© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 114164
    Prev
    Next
    INDEX
    Explanations

    question and answer pairs

    np_max-act · gemini-2.0-flash

    tokens that mark conversation structure or boundaries (start/end/header/assistant markers and the transition into the assistant's reply).

    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
     correo
    -0.07
    	op
    -0.06
    acobian
    -0.06
    .Audio
    -0.06
    conv
    -0.06
     beginners
    -0.06
    correo
    -0.06
     فلس
    -0.06
    indhoven
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     tức
    0.07
     Longer
    0.07
     Lucy
    0.07
     të
    0.06
    (parent
    0.06
    _miss
    0.06
    /topics
    0.06
    多
    0.06
    .prepare
    0.06
     дух
    0.06
    Activations Density 0.099%

    No Known Activations