Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 10513
    Prev
    Next
    INDEX
    Explanations

    Fail

    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
     Coh
    -0.07
     shop
    -0.07
     words
    -0.06
     Dodge
    -0.06
     capsules
    -0.06
     reference
    -0.06
     CHP
    -0.06
     supermarkets
    -0.06
     remedy
    -0.06
     Thomson
    -0.06
    POSITIVE LOGITS
     май
    0.07
    OOSE
    0.07
     complic
    0.07
    :%
    0.07
     Latinos
    0.06
    predict
    0.06
    /import
    0.06
    	RTDBG
    0.06
    .KeyPress
    0.06
    _edges
    0.06
    Activations Density 0.011%

    No Known Activations