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. 73078
    Prev
    Next
    INDEX
    Explanations

    say "chain"

    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
    _updated
    -0.06
    _increase
    -0.06
    ehicle
    -0.06
    ูปแบบ
    -0.06
     hotter
    -0.06
    Manufacturer
    -0.06
    found
    -0.05
     gluc
    -0.05
    _COMBO
    -0.05
    ології
    -0.05
    POSITIVE LOGITS
     �
    0.08
    BitConverter
    0.07
    偷
    0.07
     SSR
    0.07
     mais
    0.07
     başka
    0.07
    .SelectedValue
    0.07
     Millennials
    0.06
     بل
    0.06
    MaxY
    0.06
    Activations Density 0.002%

    No Known Activations