© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 57353
    Prev
    Next
    INDEX
    Explanations

    breaks, pauses

    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
     ليس
    -0.06
     ()↵
    -0.06
    OrderBy
    -0.06
    emon
    -0.06
     ElementType
    -0.06
    Vote
    -0.06
    Severity
    -0.06
     ducks
    -0.06
    _panel
    -0.06
    Points
    -0.06
    POSITIVE LOGITS
    (KERN
    0.07
    Produces
    0.06
     aftermath
    0.06
     exclusive
    0.06
     Align
    0.06
    rve
    0.06
     기반
    0.06
     Ivan
    0.06
     analsex
    0.06
     andre
    0.06
    Activations Density 0.077%

    No Known Activations