© 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 EvalsExportsinterp-engineNEWAPI 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. 94080
    Prev
    Next
    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash

    Tokens belonging to the assistant's response segment (i.e., the start/indicator of assistant-generated text).

    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
     Perception
    -0.07
    passport
    -0.07
    (Texture
    -0.07
    _reports
    -0.06
    _metrics
    -0.06
     DEN
    -0.06
     tỏ
    -0.06
    	session
    -0.06
     Kaiser
    -0.06
     specialize
    -0.06
    POSITIVE LOGITS
     gets
    0.07
    ("~
    0.06
    _ALLOW
    0.06
     Bruce
    0.06
    .Build
    0.06
    (stdout
    0.06
     democratic
    0.06
    oko
    0.06
    шку
    0.06
    26
    0.06
    Activations Density 0.136%

    No Known Activations