© 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. 30458
    Prev
    Next
    INDEX
    Explanations

    Scientific research papers

    np_max-act · gemini-2.0-flash

    The neuron is detecting mentions of specific chemical compound names (especially multi‐syllabic natural product or drug names).

    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
    rella
    -0.07
    kommen
    -0.07
    spe
    -0.07
    очно
    -0.07
     Detection
    -0.06
     istiyorum
    -0.06
     detection
    -0.06
     Ter
    -0.06
    рем
    -0.06
    ymb
    -0.06
    POSITIVE LOGITS
     sanitation
    0.06
    ：「
    0.06
     Several
    0.06
     conect
    0.06
     розроб
    0.06
     ws
    0.06
    DS
    0.06
     firma
    0.06
    __(/*!
    0.06
    _glyph
    0.06
    Activations Density 0.025%

    No Known Activations