© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110274
    Prev
    Next
    INDEX
    Explanations

    Medical re-procedures

    np_max-act · gemini-2.0-flash

    This neuron detects terms indicating repeat or subsequent treatments and procedures—chiefly words with the “re-” prefix (e.g., reoperation, re-repair, relapse, recurrent) or synonyms like “salvage.”

    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
    _none
    -0.07
     ejemplo
    -0.07
    output
    -0.07
    _ptr
    -0.07
     wrongdoing
    -0.06
     downstream
    -0.06
     comparison
    -0.06
     Crash
    -0.06
     Slate
    -0.06
    Sun
    -0.06
    POSITIVE LOGITS
     اخبار
    0.06
    935
    0.06
    gles
    0.06
    ώντας
    0.06
     UIL
    0.06
     وفي
    0.06
    лик
    0.06
     marvelous
    0.06
    (preg
    0.06
     Rt
    0.06
    Activations Density 0.021%

    No Known Activations