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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8837
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    information about roles and responsibilities in government and organizational contexts.

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

    the neuron is sensitive to numeric tokens or quantities (digits and number expressions).

    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
    、_
    -0.06
    )).
    -0.06
     малыш
    -0.06
    Spec
    -0.06
     ngồi
    -0.06
     گرفته
    -0.06
    "])
    -0.06
    concat
    -0.06
     PlayerPrefs
    -0.06
    buttons
    -0.06
    POSITIVE LOGITS
     Speaker
    0.07
     carg
    0.06
     kans
    0.06
     rogue
    0.06
     cử
    0.06
     routers
    0.06
     of
    0.06
     BIN
    0.06
     euro
    0.06
    _location
    0.06
    Activations Density 0.747%

    No Known Activations