© 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. 15-RESID-POST-AA
    11. 22837
    Prev
    Next
    INDEX
    Explanations

    production

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustering
    -0.07
     bees
    -0.07
     scattered
    -0.07
    ume
    -0.06
    [tmp
    -0.06
     mitt
    -0.06
    cab
    -0.06
    auge
    -0.06
    	mask
    -0.06
    ovíd
    -0.06
    POSITIVE LOGITS
     production
    0.08
    -production
    0.08
    楽
    0.07
    وند
    0.07
    0.07
     Winnipeg
    0.07
     Pricing
    0.07
    0.07
    on
    0.07
     purity
    0.07
    Activations Density 0.040%

    No Known Activations