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. 128285
    Prev
    Next
    INDEX
    Explanations

    misinformation

    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
     Naruto
    -0.06
     ノ
    -0.06
     اسلام
    -0.06
    و
    -0.06
    .hs
    -0.06
     předpis
    -0.06
    ー�
    -0.06
     UIAlert
    -0.06
     années
    -0.06
     شخصیت
    -0.06
    POSITIVE LOGITS
     misinformation
    0.16
    information
    0.10
    Trade
    0.07
    imiter
    0.07
    piece
    0.06
     nf
    0.06
    Verification
    0.06
     vit
    0.06
    "><?=$
    0.06
    anth
    0.06
    Activations Density 0.003%

    No Known Activations