© 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. 48385
    Prev
    Next
    INDEX
    Explanations

    Code and visual structures

    np_max-act · gemini-2.0-flash

    The neuron responds to ASCII-art/diagram or code-block style characters and line-drawing punctuation (slashes, backslashes, pipes, underscores, repeated dashes/brackets) used to make text diagrams.

    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
    _Release
    -0.07
    .pathname
    -0.07
    _SYS
    -0.07
    ITIES
    -0.07
    Setter
    -0.07
    _sent
    -0.07
    \Table
    -0.07
    _EPS
    -0.07
     verbess
    -0.07
    names
    -0.06
    POSITIVE LOGITS
    альне
    0.06
    ?),
    0.06
    	ms
    0.06
    .bt
    0.06
     chlorine
    0.06
     cevap
    0.06
     ''),↵
    0.06
    $rs
    0.06
     nov
    0.06
    аг
    0.06
    Activations Density 0.232%

    No Known Activations