© 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. 123231
    Prev
    Next
    INDEX
    Explanations

    flawed

    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
     게시판
    -0.07
    фик
    -0.06
     сох
    -0.06
     buz
    -0.06
    Nuevo
    -0.06
    NullOrEmpty
    -0.06
     compost
    -0.06
     detained
    -0.06
     up
    -0.06
    iative
    -0.06
    POSITIVE LOGITS
     flawed
    0.36
     flaws
    0.18
     flaw
    0.15
     flawless
    0.09
     doomed
    0.09
     Institution
    0.07
    _LOOP
    0.07
     Loans
    0.07
    لة
    0.07
     şu
    0.07
    Activations Density 0.003%

    No Known Activations