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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-RESID-POST-AA
    6. 103942
    Prev
    Next
    INDEX
    Explanations

    We

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .linkLabel
    -0.07
    特別
    -0.06
    esimal
    -0.06
    ++,
    -0.06
    Sci
    -0.06
     найбільш
    -0.06
     readOnly
    -0.06
    .Is
    -0.06
    .getActivity
    -0.06
    skými
    -0.06
    POSITIVE LOGITS
    _fin
    0.07
     cheer
    0.07
     Conservatives
    0.07
    ाल
    0.07
     conting
    0.06
     интер
    0.06
    بی
    0.06
     hypers
    0.06
    ท
    0.06
    磁
    0.06
    Activations Density 0.021%

    No Known Activations