Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90015
    Prev
    Next
    INDEX
    Explanations

    chemical intermediates

    np_max-act · gemini-2.0-flash

    This neuron activates on words that denote a compound’s role as an intermediate or building block (e.g. “intermediate,” “precursor,” “building block”) in chemical syntheses.

    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
    ovo
    -0.08
    Cause
    -0.07
    ParallelGroup
    -0.07
    ๑
    -0.06
     assessed
    -0.06
    _loss
    -0.06
    curities
    -0.06
    overlay
    -0.06
    _icon
    -0.06
    plot
    -0.06
    POSITIVE LOGITS
     tackle
    0.07
    isp
    0.07
    ेच
    0.06
    Traffic
    0.06
     underscores
    0.06
    _CIPHER
    0.06
    rones
    0.06
     fork
    0.06
     Kasich
    0.06
     Parsing
    0.06
    Activations Density 0.019%

    No Known Activations