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. 23-RESID-POST-AA
    6. 104063
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    내
    -0.06
     Athletic
    -0.06
     Gad
    -0.06
     Hag
    -0.06
     postgres
    -0.06
     Madame
    -0.06
     �
    -0.06
     Architect
    -0.06
    Nu
    -0.06
     gently
    -0.06
    POSITIVE LOGITS
    #else
    0.07
    .methods
    0.06
    .movies
    0.06
    .invalidate
    0.06
     постав
    0.06
    _DELAY
    0.06
     onClick
    0.06
    FUNCTION
    0.06
     clientele
    0.06
     match
    0.06
    Activations Density 0.000%

    No Known Activations