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. 27-RESID-POST-AA
    6. 108787
    Prev
    Next
    INDEX
    Explanations

    Scientific names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filmm
    -0.07
    _anim
    -0.07
     행
    -0.06
    (policy
    -0.06
    raits
    -0.06
     Counts
    -0.06
    ?',
    -0.06
     FSM
    -0.06
    Macro
    -0.06
     helium
    -0.06
    POSITIVE LOGITS
     к
    0.07
    .getExternalStorage
    0.06
    failed
    0.06
    cribing
    0.06
    ЛЬ
    0.06
     MIPS
    0.06
     отд
    0.06
     performer
    0.06
    履
    0.06
     Cont
    0.06
    Activations Density 0.014%

    No Known Activations