© 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. 3-RESID-POST-AA
    11. 93945
    Prev
    Next
    INDEX
    Explanations

    advisor

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iguiente
    -0.08
     nemoc
    -0.07
    ющих
    -0.07
    なんて
    -0.07
    >".$
    -0.07
    组织
    -0.06
    ">(
    -0.06
    acağım
    -0.06
    やる
    -0.06
    ']=$
    -0.06
    POSITIVE LOGITS
     advisor
    0.26
     Advisor
    0.20
     advisors
    0.19
     adviser
    0.19
     advisers
    0.15
     Advisors
    0.15
     Advis
    0.13
    Advisor
    0.13
    advisor
    0.10
     TripAdvisor
    0.07
    Activations Density 0.004%

    No Known Activations