© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109241
    Prev
    Next
    INDEX
    Explanations

    ampl

    np_max-act · gemini-2.0-flash

    The neuron detects technical mentions of power amplifiers (e.g. amplifier-related terms, class types, and efficiency specifications).

    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
     Що
    -0.07
     moden
    -0.06
    Hat
    -0.06
    _touch
    -0.06
    tokenizer
    -0.06
    ราค
    -0.06
    Reducer
    -0.06
    _RESOURCE
    -0.06
    anking
    -0.06
    ska
    -0.06
    POSITIVE LOGITS
     miles
    0.08
     Miles
    0.07
     самов
    0.07
     prejud
    0.07
     manslaughter
    0.07
     caching
    0.06
     μεγά
    0.06
     Chester
    0.06
     conhe
    0.06
     youths
    0.06
    Activations Density 0.003%

    No Known Activations