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

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 40014
    Prev
    Next
    INDEX
    Explanations

    Chat logs

    np_max-act · gemini-2.0-flash

    tokens marking conversation boundaries and assistant/metadata markers (e.g., end-of-turn and assistant header identifiers).

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynth
    -0.08
     ап
    -0.07
     acquiring
    -0.07
    tv
    -0.07
    ăn
    -0.06
    ibrate
    -0.06
    izr
    -0.06
     Patterson
    -0.06
    恩
    -0.06
     proced
    -0.06
    POSITIVE LOGITS
     Hey
    0.07
    Khi
    0.06
    .Fatal
    0.06
    \Data
    0.06
    vector
    0.06
    adaptiveStyles
    0.06
    Vectorizer
    0.06
     Championship
    0.06
     kaynağı
    0.06
    SCRIPTION
    0.06
    Activations Density 0.074%

    No Known Activations