© 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. 7-RESID-POST-AA
    11. 21231
    Prev
    Next
    INDEX
    Explanations

    royalty

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nějaké
    -0.07
    (Tile
    -0.07
    阳城
    -0.06
     Üniversitesi
    -0.06
     assumes
    -0.06
    際
    -0.06
    owej
    -0.06
     выб
    -0.06
    _ARROW
    -0.06
    _THRESHOLD
    -0.06
    POSITIVE LOGITS
    _plain
    0.06
     unconventional
    0.06
    '])
↵
    0.06
    .EntityManager
    0.06
    <|end_header_id|>
    0.06
    commit
    0.06
    pq
    0.06
    -proxy
    0.06
     overdose
    0.06
     después
    0.06
    Activations Density 0.087%

    No Known Activations