© 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. 120118
    Prev
    Next
    INDEX
    Explanations

    biological processes

    np_max-act · gemini-2.0-flash

    Mentions describing the formation or development of structures.

    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
    ]byte
    -0.07
     допомаг
    -0.07
    žila
    -0.07
     Controllers
    -0.07
    FileSize
    -0.07
     }}">{{
    -0.06
    hhh
    -0.06
    _clock
    -0.06
     naprost
    -0.06
     ヴ
    -0.06
    POSITIVE LOGITS
    362
    0.07
     교수
    0.06
     Type
    0.06
    JD
    0.06
    لة
    0.06
     consuming
    0.06
    illy
    0.06
    .ORDER
    0.06
     Seç
    0.06
    300
    0.06
    Activations Density 0.023%

    No Known Activations