© 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. 75673
    Prev
    Next
    INDEX
    Explanations

    plus or minus

    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
    访问
    -0.07
     dancer
    -0.07
    .rep
    -0.07
     granddaughter
    -0.06
    Miami
    -0.06
    Ended
    -0.06
     sane
    -0.06
     prisoner
    -0.06
    cidade
    -0.06
     cherish
    -0.06
    POSITIVE LOGITS
    ivy
    0.06
     mejorar
    0.06
    ців
    0.06
     exploration
    0.06
    Preferences
    0.06
     options
    0.06
    FACE
    0.06
     granite
    0.06
     kol
    0.06
     reflexivity
    0.06
    Activations Density 0.010%

    No Known Activations