Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 26459
    Prev
    Next
    INDEX
    Explanations

    rite

    np_max-act · gemini-2.0-flash

    The neuron detects “rewrite” instructions (i.e. the command to rewrite text).

    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
    Wh
    -0.07
     Lebanese
    -0.07
     intermediate
    -0.07
    零
    -0.06
     bst
    -0.06
     Fen
    -0.06
    OVER
    -0.06
    Mo
    -0.06
     peu
    -0.06
    剑
    -0.06
    POSITIVE LOGITS
    |)↵
    0.07
     spolup
    0.07
    _signals
    0.06
     Kadın
    0.06
    >/<
    0.06
    >Returns
    0.06
     Toastr
    0.06
    /backend
    0.06
     also
    0.06
     Bí
    0.06
    Activations Density 0.034%

    No Known Activations