© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12556
    Prev
    Next
    INDEX
    Explanations

    relief

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the term “relief” (especially in the phrase “denying relief on”) in legal opinion texts.

    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
     granny
    -0.07
    umont
    -0.06
     fotos
    -0.06
     인터
    -0.06
     Zap
    -0.06
    ınızı
    -0.06
    (pages
    -0.06
    `]
    -0.06
    =p
    -0.06
     Ning
    -0.06
    POSITIVE LOGITS
    救
    0.08
     relief
    0.08
    .Alignment
    0.07
    HA
    0.07
    ;-
    0.07
     cls
    0.07
     lifting
    0.07
    _acl
    0.07
     Gle
    0.06
     Relief
    0.06
    Activations Density 0.002%

    No Known Activations