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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 94633
    Prev
    Next
    INDEX
    Explanations

    UVA UVB

    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
     ye
    -0.07
     Nit
    -0.07
     داو
    -0.07
    panied
    -0.06
     ::::::::
    -0.06
     punk
    -0.06
     Через
    -0.06
     ní
    -0.06
     tactile
    -0.06
    chains
    -0.06
    POSITIVE LOGITS
     BOOL
    0.11
    _rows
    0.10
     exon
    0.08
    _comments
    0.07
    VA
    0.07
     SOLUTION
    0.06
     ψ
    0.06
    friend
    0.06
    cljs
    0.06
    .imageView
    0.06
    Activations Density 0.004%

    No Known Activations