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. 19-RESID-POST-AA
    6. 45030
    Prev
    Next
    INDEX
    Explanations

    )

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exercise
    -0.07
    manufact
    -0.06
     LinkedList
    -0.06
    ッシュ
    -0.06
     deterministic
    -0.06
     simplement
    -0.06
     Players
    -0.06
    PEndPoint
    -0.06
    -enable
    -0.06
     öden
    -0.06
    POSITIVE LOGITS
     =================
    0.07
    pn
    0.07
     Figures
    0.07
     kel
    0.07
    .hl
    0.07
    Bitcoin
    0.06
    .Marker
    0.06
     Flores
    0.06
     Tone
    0.06
     ساعت
    0.06
    Activations Density 0.107%

    No Known Activations