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. 122927
    Prev
    Next
    INDEX
    Explanations

    magazines

    np_max-act · gemini-2.0-flash
    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
    ソン
    -0.07
    ACKET
    -0.06
    教
    -0.06
     Cuomo
    -0.06
    Ord
    -0.06
     disturbing
    -0.06
     sanity
    -0.06
    uri
    -0.06
     cạnh
    -0.06
    ันก
    -0.06
    POSITIVE LOGITS
     sanitized
    0.06
    _signal
    0.06
    :UIControlStateNormal
    0.06
    .facebook
    0.06
    _ce
    0.06
    munition
    0.06
    .buy
    0.06
    ]",↵
    0.06
     deleteUser
    0.06
     InternalEnumerator
    0.06
    Activations Density 0.011%

    No Known Activations