© 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. 77109
    Prev
    Next
    INDEX
    Explanations

    Negative informational text snippets

    np_max-act · gemini-2.0-flash

    discourse markers and structural cue phrases that signal contrast, summary, listing, scope, or framing within explanatory text and Q&A transcripts.

    oai_token-act-pair · gpt-5Triggered 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
     Sith
    -0.08
    loud
    -0.06
     ब
    -0.06
    恩
    -0.06
     Suz
    -0.06
     Jasper
    -0.06
     ده
    -0.06
     Sec
    -0.06
     failure
    -0.06
    Bin
    -0.06
    POSITIVE LOGITS
    ”).
    0.06
    然
    0.06
     interven
    0.06
     obou
    0.06
    とき
    0.06
    #+
    0.06
     연락
    0.06
    .Host
    0.06
    "]->
    0.06
    --)↵
    0.06
    Activations Density 0.197%

    No Known Activations