© 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. 11-RESID-POST-AA
    11. 22692
    Prev
    Next
    INDEX
    Explanations

    transferring to a medium

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sane
    -0.08
    rhs
    -0.07
    (kv
    -0.07
    -php
    -0.07
     جنگ
    -0.07
    Intro
    -0.06
     jog
    -0.06
     ух
    -0.06
     folders
    -0.06
    _age
    -0.06
    POSITIVE LOGITS
    ??↵↵
    0.07
     elit
    0.07
     outer
    0.06
     territorial
    0.06
     tỉ
    0.06
     aspiring
    0.06
     Ре
    0.06
     =
↵
    0.06
     central
    0.06
     【
    0.06
    Activations Density 0.092%

    No Known Activations