© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9469
    Prev
    Next
    INDEX
    Explanations

    nouns

    np_max-act · gemini-2.0-flash

    This neuron detects references to online content units—words like “news,” “articles,” “sources,” “page,” and “key points” that denote parts of a web document.

    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
    gent
    -0.08
    .tax
    -0.06
    LEAR
    -0.06
    GROUP
    -0.06
    	ax
    -0.06
    _TERM
    -0.06
     найбільш
    -0.06
     precursor
    -0.06
     Εν
    -0.06
    PTION
    -0.06
    POSITIVE LOGITS
     věci
    0.07
     června
    0.06
     sna
    0.06
    usuarios
    0.06
    .NaN
    0.06
     DAG
    0.06
    иж
    0.06
     března
    0.06
    _attempt
    0.05
    Styles
    0.05
    Activations Density 0.045%

    No Known Activations