© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 118864
    Prev
    Next
    INDEX
    Explanations

    links

    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
    过来
    -0.07
    427
    -0.06
     le
    -0.06
    896
    -0.06
    (plan
    -0.06
     kidneys
    -0.06
     according
    -0.06
     la
    -0.06
    ang
    -0.06
    ’n
    -0.06
    POSITIVE LOGITS
     @{↵
    0.07
     연구
    0.06
    .EX
    0.06
    θεση
    0.06
     Vys
    0.06
     carve
    0.06
     Εξ
    0.06
     identifiable
    0.06
     constexpr
    0.06
    yyvsp
    0.06
    Activations Density 0.039%

    No Known Activations