© 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. 28078
    Prev
    Next
    INDEX
    Explanations

    single quote

    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
    ethyst
    -0.07
    aterial
    -0.06
     Trom
    -0.06
     tamp
    -0.06
     bowel
    -0.06
     воздейств
    -0.06
    altern
    -0.05
    .Line
    -0.05
    oton
    -0.05
     dame
    -0.05
    POSITIVE LOGITS
    notated
    0.07
     Lookup
    0.07
     Proceedings
    0.07
     talep
    0.07
    University
    0.07
     University
    0.07
    '")↵
    0.07
    .split
    0.07
     femmes
    0.07
     Mot
    0.07
    Activations Density 0.000%

    No Known Activations