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. 23-RESID-POST-AA
    6. 7565
    Prev
    Next
    INDEX
    Explanations

    Prices in Euros

    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
    $L
    -0.07
     advisors
    -0.07
    Forest
    -0.06
     Tong
    -0.06
    试
    -0.06
     Code
    -0.06
     شرق
    -0.06
    Dep
    -0.06
     hinge
    -0.06
     l
    -0.06
    POSITIVE LOGITS
    .setVerticalGroup
    0.07
    .arch
    0.07
    avigation
    0.06
     relate
    0.06
    (Config
    0.06
    .clipsToBounds
    0.06
    .warning
    0.06
    medium
    0.06
     onOptionsItemSelected
    0.06
    anlı
    0.06
    Activations Density 0.021%

    No Known Activations