© 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. 73651
    Prev
    Next
    INDEX
    Explanations

    beer reviews

    np_max-act · gemini-2.0-flash

    This neuron detects sensory descriptors of flavor and aroma (e.g. words describing taste, mouthfeel, or scent notes).

    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
     stance
    -0.07
     Только
    -0.07
     One
    -0.07
     infographic
    -0.07
    tele
    -0.07
    sup
    -0.07
     prefers
    -0.07
     ery
    -0.07
    Luckily
    -0.07
     one
    -0.07
    POSITIVE LOGITS
    εχ
    0.07
    \<
    0.07
    :g
    0.06
     ){↵
    0.06
    ♀
    0.06
     gezocht
    0.06
    CFG
    0.06
    (json
    0.06
    646
    0.06
     Europ
    0.06
    Activations Density 0.011%

    No Known Activations