© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 110143
    Prev
    Next
    INDEX
    Explanations

    a

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    есп
    -0.07
    -independent
    -0.07
    erez
    -0.06
     waves
    -0.06
    urm
    -0.06
    Dist
    -0.06
     QSize
    -0.06
    blank
    -0.06
    Segment
    -0.06
    (levels
    -0.06
    POSITIVE LOGITS
    ffe
    0.06
    -serif
    0.06
    ože
    0.06
    :pointer
    0.06
    iversite
    0.06
    .active
    0.06
     khá
    0.06
     більше
    0.05
     jugador
    0.05
     zas
    0.05
    Activations Density 0.016%

    No Known Activations