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. 1042
    Prev
    Next
    INDEX
    Explanations

    oph

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the word “eosinophil” (and its subparts), i.e. references to eosinophil cells.

    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
    posts
    -0.06
     Σα
    -0.06
    illance
    -0.06
     intestinal
    -0.06
     ad
    -0.06
     NTN
    -0.06
     sneak
    -0.06
     territory
    -0.06
    uls
    -0.06
    -between
    -0.06
    POSITIVE LOGITS
    .long
    0.07
    pok
    0.07
     codecs
    0.06
    _good
    0.06
    .close
    0.06
    /network
    0.06
    parseFloat
    0.06
     français
    0.06
    LOAT
    0.06
    _forms
    0.06
    Activations Density 0.001%

    No Known Activations