© 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. 8784
    Prev
    Next
    INDEX
    Explanations

    Education costs

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of monetary amounts and cost-related terms (prices, fees, tuition, dollar figures, and similar).

    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
     van
    -0.07
     تخصصی
    -0.06
     Δημο
    -0.06
    schedule
    -0.06
    edula
    -0.06
    割
    -0.06
    _TER
    -0.06
    _twitter
    -0.06
    _None
    -0.06
    .timestamp
    -0.06
    POSITIVE LOGITS
    	cli
    0.06
    299
    0.06
    ΟΚ
    0.06
     chương
    0.06
    (pc
    0.06
    encv
    0.06
    dob
    0.06
    ierte
    0.06
    ycz
    0.06
    DEC
    0.06
    Activations Density 0.008%

    No Known Activations