Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 7599
    Prev
    Next
    INDEX
    Explanations

    Code and programming tips

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     matchup
    -0.07
     objected
    -0.07
    -metal
    -0.06
    ию
    -0.06
     сейчас
    -0.06
    品
    -0.06
    .article
    -0.06
     minors
    -0.06
     ansible
    -0.06
     Siemens
    -0.06
    POSITIVE LOGITS
    alarda
    0.06
     baff
    0.06
    AGER
    0.06
     Veget
    0.06
    LogLevel
    0.06
    PCP
    0.06
    .Web
    0.06
     Invent
    0.06
     Switch
    0.06
     Ή
    0.06
    Activations Density 0.072%

    No Known Activations