© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56733
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash

    terms related to tasks and methods in academic or technical contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects tokens that are part of the extracted supply‐and‐demand information fields (i.e. the entity names and quantities inside the JSON output values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ije
    -0.07
     awake
    -0.07
    prites
    -0.06
    _USERS
    -0.06
    UCE
    -0.06
    èn
    -0.06
     застав
    -0.06
     bent
    -0.06
    bject
    -0.06
    aphore
    -0.06
    POSITIVE LOGITS
     kort
    0.06
    _TS
    0.06
     trval
    0.06
     representing
    0.06
    _is
    0.06
    /ubuntu
    0.06
     červ
    0.06
    SERVICE
    0.06
     "'"
    0.06
     trabaj
    0.06
    Activations Density 0.010%

    No Known Activations