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. 109067
    Prev
    Next
    INDEX
    Explanations

    Properties/measurements

    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
    principal
    -0.07
     SECRET
    -0.06
    true
    -0.06
    qh
    -0.06
    -root
    -0.06
    .render
    -0.06
    queryString
    -0.06
    ести
    -0.06
    ofday
    -0.06
    key
    -0.06
    POSITIVE LOGITS
    送
    0.07
    가능
    0.07
     يم
    0.07
    .AddScoped
    0.07
    표
    0.07
    atched
    0.07
     가능
    0.07
    .AddTransient
    0.07
     proficiency
    0.06
    उ
    0.06
    Activations Density 0.059%

    No Known Activations