© 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. 6895
    Prev
    Next
    INDEX
    Explanations

    Opening quote

    np_max-act · gemini-2.0-flash

    This neuron fires on quoted string literals (text enclosed in single, double, or triple quotes).

    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
     Bibli
    -0.07
    RICS
    -0.07
    .Bottom
    -0.06
     ALSO
    -0.06
    amak
    -0.06
    nim
    -0.06
    .plugins
    -0.06
    :
    -0.06
    orneys
    -0.06
    /sidebar
    -0.06
    POSITIVE LOGITS
     (@
    0.08
     ("
    0.07
     ($
    0.07
    _dot
    0.07
    _ue
    0.07
     acept
    0.06
                                                                                       
    0.06
    ADO
    0.06
    (ht
    0.06
     ('
    0.06
    Activations Density 0.016%

    No Known Activations