© 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. 11-RESID-POST-AA
    11. 51443
    Prev
    Next
    INDEX
    Explanations

    Non-grammatical text

    np_max-act · gemini-2.0-flash

    instructional or task-oriented prompt language (imperative/meta prompts asking the assistant to perform or follow procedures).

    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_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
    uez
    -0.07
    utta
    -0.07
     jumlah
    -0.07
    TRAIN
    -0.07
     ed
    -0.06
     ions
    -0.06
     Directors
    -0.06
     directors
    -0.06
     checked
    -0.06
     leaves
    -0.06
    POSITIVE LOGITS
     interv
    0.08
    711
    0.07
    访问
    0.06
    VertexAttribArray
    0.06
    ruptions
    0.06
    684
    0.06
     LAT
    0.06
    /language
    0.06
     seventy
    0.06
     prat
    0.06
    Activations Density 0.470%

    No Known Activations