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. 30858
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
     apoptosis
    -0.07
    -growing
    -0.06
     Diameter
    -0.06
     games
    -0.06
     Problems
    -0.06
     Maine
    -0.06
    leted
    -0.06
    	and
    -0.06
    anneer
    -0.06
    -save
    -0.06
    POSITIVE LOGITS
    EPS
    0.07
     Ebony
    0.06
    nocení
    0.06
     pcm
    0.06
     спря
    0.06
     eventId
    0.06
     عش
    0.06
    	me
    0.06
    _THRESH
    0.06
     घर
    0.06
    Activations Density 0.002%

    No Known Activations