Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41947
    Prev
    Next
    INDEX
    Explanations

    ybrid

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of protein–protein interaction assays (e.g. yeast two-hybrid, co-immunoprecipitation, binding assays).

    oai_token-act-pair · o4-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
    (ep
    -0.06
    /error
    -0.06
     commons
    -0.06
    PLAY
    -0.06
     puis
    -0.06
     stories
    -0.06
     players
    -0.06
     البي
    -0.06
    _PP
    -0.06
    背
    -0.06
    POSITIVE LOGITS
     stationed
    0.07
     Detect
    0.07
     中国
    0.07
     Northwestern
    0.06
    σ
    0.06
     Northwest
    0.06
    vale
    0.06
     كس
    0.06
    、“
    0.06
     постро
    0.06
    Activations Density 0.007%

    No Known Activations