© 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. 109447
    Prev
    Next
    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive phrases that label compounds as “small” (e.g. “small peptide,” “small molecule”) and specify their molecular characteristics (like molecular weight ranges).

    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
     Nadu
    -0.08
     milk
    -0.06
     Cre
    -0.06
     ;;^
    -0.06
     ге
    -0.06
    (',')
    -0.06
    ють
    -0.06
     가정
    -0.06
     Buster
    -0.06
    浦
    -0.06
    POSITIVE LOGITS
     younger
    0.07
     مفهوم
    0.07
     专
    0.07
    lobal
    0.06
     producing
    0.06
     awaiting
    0.06
    pub
    0.06
    ีพ
    0.06
    search
    0.06
    /support
    0.06
    Activations Density 0.008%

    No Known Activations