© 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. 110220
    Prev
    Next
    INDEX
    Explanations

    therm

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of thermoplastic (and related “therm-” polymer) materials.

    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
    adius
    -0.08
    ical
    -0.07
    lal
    -0.07
     Dal
    -0.07
     clan
    -0.07
     Clan
    -0.07
     لأن
    -0.06
     Gray
    -0.06
     Attack
    -0.06
     Cities
    -0.06
    POSITIVE LOGITS
     Therm
    0.12
     therm
    0.12
     thermo
    0.09
     Theresa
    0.08
     Thompson
    0.08
     thermostat
    0.08
     temper
    0.08
    IRM
    0.08
    Teacher
    0.08
    -next
    0.07
    Activations Density 0.006%

    No Known Activations