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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 35601
    Prev
    Next
    INDEX
    Explanations

    sequence

    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
    busters
    -0.07
    .AddParameter
    -0.07
    相
    -0.07
     Robbie
    -0.06
     никто
    -0.06
     بها
    -0.06
    ्वत
    -0.06
    ovo
    -0.06
    Dll
    -0.06
    PRI
    -0.06
    POSITIVE LOGITS
     rejo
    0.07
     archae
    0.07
    alore
    0.07
     skeletons
    0.07
     torrent
    0.06
    월까지
    0.06
    UTDOWN
    0.06
     stro
    0.06
     davran
    0.06
     جمهوری
    0.06
    Activations Density 0.009%

    No Known Activations