© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89064
    Prev
    Next
    INDEX
    Explanations

    economic news reports

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the economic‐data release schedule—words like “releases,” “schedule,” “quiet,” and related calendar terms indicating when data come out.

    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
    .Txt
    -0.07
    _scope
    -0.07
     Voor
    -0.07
     StyleSheet
    -0.07
    ortion
    -0.06
    чна
    -0.06
     Kal
    -0.06
     mating
    -0.06
     Českosloven
    -0.06
     Mitarbeiter
    -0.06
    POSITIVE LOGITS
    'être
    0.06
    31
    0.06
    .Bad
    0.06
     granite
    0.06
    anger
    0.06
     şik
    0.06
    "testing
    0.06
     maxY
    0.06
    _datas
    0.06
    .bumptech
    0.06
    Activations Density 0.014%

    No Known Activations