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. 7-RESID-POST-AA
    6. 18892
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    卫
    -0.07
    З
    -0.07
    Ин
    -0.07
    chn
    -0.07
    ζ
    -0.06
     близ
    -0.06
    _mv
    -0.06
     deutschland
    -0.06
    -з
    -0.06
     Later
    -0.06
    POSITIVE LOGITS
     SOM
    0.06
     porad
    0.06
     numRows
    0.06
    boxed
    0.06
    '],'
    0.06
     dostate
    0.06
    머니
    0.06
    ้านด
    0.06
    <|begin_of_text|>
    0.06
    /questions
    0.06
    Activations Density 0.185%

    No Known Activations