© 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. 109884
    Prev
    Next
    INDEX
    Explanations

    choose

    np_max-act · gemini-2.0-flash

    The neuron activates on words that express making a choice—i.e. forms of “choose” (chose, chosen).

    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
     resigned
    -0.08
     worlds
    -0.07
     lady
    -0.07
     durch
    -0.07
     sidebar
    -0.07
     Bened
    -0.07
    children
    -0.06
     г
    -0.06
     Linked
    -0.06
    àn
    -0.06
    POSITIVE LOGITS
    ==="
    0.06
     choose
    0.06
    $img
    0.06
    .alignment
    0.06
     chose
    0.06
    �
    0.06
     onChangeText
    0.06
     україн
    0.06
    _likelihood
    0.06
    умов
    0.06
    Activations Density 0.019%

    No Known Activations