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. 15-RESID-POST-AA
    6. 20348
    Prev
    Next
    INDEX
    Explanations

    to

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Flat
    -0.06
    .strings
    -0.06
    丘
    -0.06
    /k
    -0.06
    音樂
    -0.06
    -qu
    -0.06
     萬
    -0.06
     считается
    -0.06
    .bl
    -0.06
     Sirius
    -0.06
    POSITIVE LOGITS
    /REC
    0.06
    :SetText
    0.06
    ')]
    0.06
     RESET
    0.06
     issuer
    0.06
     regret
    0.06
    (jq
    0.06
    �
    0.06
     Gore
    0.06
    quir
    0.06
    Activations Density 0.018%

    No Known Activations