© 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. 90593
    Prev
    Next
    INDEX
    Explanations

    philosophy

    np_max-act · gemini-2.0-flash

    The neuron activates on scholarly or theoretical terms and the names of academics, i.e. references to academic concepts or author names.

    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
    _indices
    -0.06
     lord
    -0.06
    朋友
    -0.06
    PLAYER
    -0.06
     开始
    -0.06
     deterior
    -0.06
     бенз
    -0.05
     bumps
    -0.05
     counterparts
    -0.05
     光
    -0.05
    POSITIVE LOGITS
    ::::::::::
    0.08
     Eston
    0.07
     fringe
    0.07
    ะ
    0.06
    мом
    0.06
    striction
    0.06
    .setLevel
    0.06
    .Stack
    0.06
    alive
    0.06
    .createUser
    0.06
    Activations Density 0.024%

    No Known Activations