© 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. 15-RESID-POST-AA
    6. 4147
    Prev
    Next
    INDEX
    Explanations

    Code/Software

    np_max-act · gemini-2.0-flash

    The neuron detects code-like tokens and programming syntax — technical identifiers and symbols found in source code.

    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
     lounge
    -0.07
    /bower
    -0.07
    .Send
    -0.07
    .cookies
    -0.07
     shocking
    -0.06
    _messages
    -0.06
    airobi
    -0.06
    _almost
    -0.06
    سان
    -0.06
    _loop
    -0.06
    POSITIVE LOGITS
    CLUSION
    0.06
    liked
    0.06
     mediante
    0.06
    ordo
    0.06
     NE
    0.06
    ária
    0.06
    …”↵↵
    0.06
     após
    0.06
     através
    0.06
    ertz
    0.06
    Activations Density 0.034%

    No Known Activations