© 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. 7521
    Prev
    Next
    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the token “out” (including as part of hyphenated or multiword expressions).

    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
    blem
    -0.08
     Mercy
    -0.07
     Vì
    -0.07
     Penny
    -0.07
    endency
    -0.07
     Cec
    -0.07
     Jeremy
    -0.07
     Kelly
    -0.07
     Gee
    -0.07
    되지
    -0.07
    POSITIVE LOGITS
     out
    0.18
     Out
    0.17
    Out
    0.15
     OUT
    0.15
    OUT
    0.15
    out
    0.15
    -out
    0.14
    -Out
    0.12
    	out
    0.12
    _out
    0.12
    Activations Density 0.114%

    No Known Activations