© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20591
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    instructions that set up a two-entity, turn‑taking roleplay or game (detailed meta‑rules about how the conversation or words should be exchanged).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    iber
    -0.07
     clusters
    -0.07
     obtain
    -0.07
     far
    -0.06
    са
    -0.06
     extracts
    -0.06
     coloring
    -0.06
     Howe
    -0.06
    PD
    -0.06
     rivalry
    -0.06
    POSITIVE LOGITS
     reflexivity
    0.07
    _GREEN
    0.07
    .Query
    0.07
     InvalidOperationException
    0.06
    ‌تواند
    0.06
    discussion
    0.06
     userProfile
    0.06
     srp
    0.06
    _logits
    0.06
    yleft
    0.06
    Activations Density 0.005%

    No Known Activations