© 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 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. 23507
    Prev
    Next
    INDEX
    Explanations

    Punctuation and conversational fillers

    np_max-act · gemini-2.0-flash

    short, positive conversational acknowledgements—brief greetings, praises, or exclamatory responses.

    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
     наук
    -0.07
    .mon
    -0.06
    ATYPE
    -0.06
    _FA
    -0.06
     numberOfRowsInSection
    -0.06
    ises
    -0.06
    ३
    -0.06
     qry
    -0.06
     Joomla
    -0.06
     dvěma
    -0.06
    POSITIVE LOGITS
     Shot
    0.07
    <Void
    0.07
     работ
    0.06
     scissors
    0.06
     symbolic
    0.06
     artist
    0.06
     expecting
    0.06
     voy
    0.06
     artists
    0.06
     disc
    0.06
    Activations Density 0.066%

    No Known Activations