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. 19-RESID-POST-AA
    6. 110629
    Prev
    Next
    INDEX
    Explanations

    example

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "With
    -0.08
    ؤال
    -0.07
    aturdays
    -0.06
    orem
    -0.06
    ("")
    -0.06
     clown
    -0.06
     Bern
    -0.06
     Starbucks
    -0.06
     стены
    -0.06
    Badge
    -0.06
    POSITIVE LOGITS
    Launcher
    0.06
     effic
    0.06
     FL
    0.06
     Unter
    0.06
    MATRIX
    0.06
     SUR
    0.06
     %(
    0.06
     eating
    0.06
     Spencer
    0.06
    _requests
    0.06
    Activations Density 0.006%

    No Known Activations