© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129702
    Prev
    Next
    INDEX
    Explanations

    fuel/oil

    np_max-act · gemini-2.0-flash

    This neuron consistently flags specific petroleum fuel and distillate product names (e.g. “distillate,” “jet fuel,” “diesel,” “gas oils,” “kerosene”).

    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
    Flo
    -0.07
    erule
    -0.07
    لو
    -0.06
    .Pos
    -0.06
     spam
    -0.06
    豊
    -0.06
     Něm
    -0.06
    ození
    -0.06
    Cd
    -0.06
    ierung
    -0.06
    POSITIVE LOGITS
     sticky
    0.06
    TextField
    0.06
    Previously
    0.06
     famously
    0.06
     différents
    0.06
     gradual
    0.06
    建议
    0.06
     Until
    0.06
     Public
    0.06
    ph
    0.06
    Activations Density 0.011%

    No Known Activations