© 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. 19-RESID-POST-AA
    11. 29727
    Prev
    Next
    INDEX
    Explanations

    ha

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     off
    -0.09
    เรา
    -0.07
    状态
    -0.07
     squeez
    -0.06
     CascadeType
    -0.06
     poem
    -0.06
     hinge
    -0.06
    ':''
    -0.06
    arLayout
    -0.06
    incl
    -0.06
    POSITIVE LOGITS
    ertainment
    0.07
     Fri
    0.07
    ricane
    0.07
     underwater
    0.06
    Iran
    0.06
    cloth
    0.06
    -comments
    0.06
     homosexual
    0.06
     CONVERT
    0.06
    attempt
    0.06
    Activations Density 0.030%

    No Known Activations