© 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. 118991
    Prev
    Next
    INDEX
    Explanations

    fashion

    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
     optimizing
    -0.07
    -capital
    -0.07
    -hash
    -0.07
    (cap
    -0.07
     '+'
    -0.07
    901
    -0.07
    uint
    -0.06
    Mis
    -0.06
    cum
    -0.06
    _ghost
    -0.06
    POSITIVE LOGITS
     ward
    0.06
     Yani
    0.06
     associate
    0.06
     inj
    0.06
    CLI
    0.06
     Smithsonian
    0.06
    在线阅读
    0.06
    urate
    0.06
     Examiner
    0.06
     گیرد
    0.06
    Activations Density 0.065%

    No Known Activations