© 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. 110164
    Prev
    Next
    INDEX
    Explanations

    rule

    np_max-act · gemini-2.0-flash

    This neuron detects references to rule‐based expert systems and decision‐tree reasoning (e.g., expert systems, MYCIN, rule-based, decision trees).

    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
    Putin
    -0.07
     Contractors
    -0.06
    Attrib
    -0.06
    لاف
    -0.06
    lyph
    -0.06
     Maryland
    -0.06
    Precision
    -0.06
    ore
    -0.06
     slain
    -0.06
     packed
    -0.06
    POSITIVE LOGITS
     گن
    0.07
     yandan
    0.07
     правда
    0.06
    ние
    0.06
    InputLabel
    0.06
     giản
    0.06
     haciendo
    0.06
     ingres
    0.06
     hvor
    0.06
    823
    0.06
    Activations Density 0.024%

    No Known Activations