© 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. 28055
    Prev
    Next
    INDEX
    Explanations

    ic

    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
    _SHORT
    -0.07
    [number
    -0.06
     parade
    -0.06
     Cham
    -0.06
     exploded
    -0.06
     उत
    -0.06
     terrific
    -0.06
     obou
    -0.06
     Problems
    -0.06
     churches
    -0.05
    POSITIVE LOGITS
     StringTokenizer
    0.08
     Newfoundland
    0.07
     GC
    0.07
     genel
    0.07
     Disc
    0.07
    /************************************************
    0.07
    γγελ
    0.07
    �細
    0.07
     Gene
    0.07
    bell
    0.06
    Activations Density 0.004%

    No Known Activations