© 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. 30520
    Prev
    Next
    INDEX
    Explanations

    Science and Technology

    np_max-act · gemini-2.0-flash

    scientific or technical research–style language (clinical studies, methods, industrial/engineering terms and related jargon).

    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
     Clinic
    -0.07
     clinic
    -0.07
     تشخیص
    -0.07
    ड
    -0.06
    θούν
    -0.06
    ائ
    -0.06
    漏
    -0.06
     Pharma
    -0.06
    iac
    -0.06
    Fashion
    -0.06
    POSITIVE LOGITS
    sentence
    0.08
    (account
    0.07
    ']],
    0.07
    .•
    0.06
    .`
    0.06
    (preg
    0.06
    .findall
    0.06
     Azerbai
    0.06
     clauses
    0.06
    estate
    0.06
    Activations Density 0.468%

    No Known Activations