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. 103949
    Prev
    Next
    INDEX
    Explanations

    violent actions

    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
    office
    -0.07
    minated
    -0.07
    ifers
    -0.07
     evaluations
    -0.07
    court
    -0.07
     Parameters
    -0.07
    Arena
    -0.07
    Contracts
    -0.07
    icle
    -0.07
    KN
    -0.07
    POSITIVE LOGITS
    ,response
    0.06
     fark
    0.06
     licking
    0.06
    orrar
    0.06
     classy
    0.06
     ripping
    0.06
     personas
    0.06
    IBAction
    0.05
    'options
    0.05
     elimin
    0.05
    Activations Density 0.039%

    No Known Activations