© 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. 11-RESID-POST-AA
    11. 72689
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS code

    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
    ReLU
    -0.08
    pretty
    -0.07
    .summary
    -0.07
     hormone
    -0.07
    文字
    -0.07
    _labels
    -0.07
    	NullCheck
    -0.07
     headache
    -0.06
     innocence
    -0.06
    METHOD
    -0.06
    POSITIVE LOGITS
     رأ
    0.07
    etermin
    0.06
     errone
    0.06
     reim
    0.06
    kili
    0.06
    errer
    0.06
     Bene
    0.06
     jitter
    0.06
    istinguish
    0.05
    iciar
    0.05
    Activations Density 0.011%

    No Known Activations