© 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. 577
    Prev
    Next
    INDEX
    Explanations

    ens

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect the term “desensitization” (and its variants like down-regulation or resensitization) describing receptor desensitization processes.

    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
     मश
    -0.07
    _word
    -0.06
    oň
    -0.06
    .ResponseEntity
    -0.06
    tréal
    -0.06
    스토
    -0.06
    ası
    -0.06
    uncio
    -0.06
     Thanksgiving
    -0.06
     throat
    -0.06
    POSITIVE LOGITS
    rpc
    0.06
    (exception
    0.06
     progress
    0.06
    -striped
    0.06
     област
    0.06
    ため
    0.06
     squadron
    0.06
     تعیین
    0.06
    $_
    0.06
     transform
    0.06
    Activations Density 0.005%

    No Known Activations