© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 104957
    Prev
    Next
    INDEX
    Explanations

    biodiversity

    np_max-act · gemini-2.0-flash

    references to human impacts and interactions with ecosystems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EX
    -0.06
     readings
    -0.06
     N
    -0.06
     Roose
    -0.06
     grammar
    -0.06
     ass
    -0.06
    kea
    -0.06
    得
    -0.06
    CHO
    -0.06
    WASHINGTON
    -0.06
    POSITIVE LOGITS
     ></
    0.07
     biodiversity
    0.06
     nokt
    0.06
     фот
    0.06
     Shuffle
    0.06
    evi
    0.06
    fid
    0.06
    =array
    0.06
     AttributeError
    0.06
    .:.:.:.:.:.:.:.:
    0.06
    Activations Density 0.008%

    No Known Activations