© 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. 61131
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and Initials

    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
    vore
    -0.07
     قیمت
    -0.07
     classname
    -0.07
    bv
    -0.07
    Surv
    -0.07
     archit
    -0.06
    pm
    -0.06
    Accessor
    -0.06
    -at
    -0.06
    seq
    -0.06
    POSITIVE LOGITS
    羽
    0.06
     Hel
    0.06
    ETCH
    0.06
    ObjectContext
    0.06
    IV
    0.06
    grab
    0.06
     CGAffineTransform
    0.06
    řet
    0.06
    ermen
    0.06
    -generator
    0.06
    Activations Density 0.205%

    No Known Activations