© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 42859
    Prev
    Next
    INDEX
    Explanations

    Adjusted earnings

    np_max-act · gemini-2.0-flash

    This neuron detects financial‐report terminology and section headings (e.g. “GAAP,” “Adjusted,” “EBITDA,” “reconciliations,” “non-GAAP”) in earnings‐report text.

    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
    Luc
    -0.06
     scarf
    -0.06
     Fest
    -0.06
    ,这
    -0.06
    lock
    -0.06
    Hel
    -0.06
    sitemap
    -0.06
    шка
    -0.06
     NULL
    -0.06
     Pack
    -0.06
    POSITIVE LOGITS
    þ
    0.07
    equals
    0.07
     youth
    0.07
    .Inner
    0.06
    :event
    0.06
    _weather
    0.06
     counselor
    0.06
     applications
    0.06
    actical
    0.06
    >.↵
    0.06
    Activations Density 0.004%

    No Known Activations