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. 3-RESID-POST-AA
    6. 121951
    Prev
    Next
    INDEX
    Explanations

    check boxes

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gol
    -0.08
     borough
    -0.07
    _OP
    -0.07
    Chip
    -0.07
    _any
    -0.07
     unary
    -0.07
    -place
    -0.07
    :p
    -0.06
     critically
    -0.06
     گروه
    -0.06
    POSITIVE LOGITS
    artisanlib
    0.07
     mundane
    0.07
     Synd
    0.07
     mệ
    0.06
     стрем
    0.06
     Strom
    0.06
     disputes
    0.06
    srv
    0.06
     verification
    0.06
     columnist
    0.06
    Activations Density 0.051%

    No Known Activations