© 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
    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. 89173
    Prev
    Next
    INDEX
    Explanations

    code, file paths

    np_max-act · gemini-2.0-flash

    The neuron activates on placeholder tokens of the form “NAME_<…>” (i.e. user‐provided name identifiers).

    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
     descon
    -0.07
    또
    -0.06
     κρα
    -0.06
    不到
    -0.06
     Smarty
    -0.06
    ')}}">↵
    -0.06
    fried
    -0.06
    Mos
    -0.06
     둘
    -0.06
    _Ass
    -0.06
    POSITIVE LOGITS
    DN
    0.07
    Navigation
    0.07
    -yard
    0.07
    ;}
    0.06
    basic
    0.06
    GREE
    0.06
     yard
    0.06
    centroid
    0.06
     Strand
    0.06
    نجليزية
    0.06
    Activations Density 0.022%

    No Known Activations