© 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. 109795
    Prev
    Next
    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the morpheme “sub” (especially in the word “subproject”).

    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
    .mark
    -0.08
     regex
    -0.07
    _packet
    -0.06
    _none
    -0.06
    _et
    -0.06
    	io
    -0.06
     essays
    -0.06
    _dead
    -0.06
    iri
    -0.06
     ilma
    -0.06
    POSITIVE LOGITS
    ्‍
    0.07
    Jack
    0.07
    (BASE
    0.07
    athers
    0.07
    訓
    0.06
    搞
    0.06
    겠
    0.06
     chtě
    0.06
    "?↵↵
    0.06
    ới
    0.06
    Activations Density 0.001%

    No Known Activations