© 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. 129762
    Prev
    Next
    INDEX
    Explanations

    C/C++ functions

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of C standard‐library identifiers (especially functions like atoi, strtok, malloc, and the stdlib.h header).

    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
    abwe
    -0.06
     사라
    -0.06
     �
    -0.06
    trimmed
    -0.06
     tego
    -0.06
     Abstract
    -0.06
     žádný
    -0.06
    heatmap
    -0.06
     než
    -0.06
    InternalEnumerator
    -0.06
    POSITIVE LOGITS
    (mapStateToProps
    0.07
    ious
    0.07
    	require
    0.07
     libre
    0.06
     Js
    0.06
    -guide
    0.06
    .StoredProcedure
    0.06
     cords
    0.06
    	assert
    0.06
     sacrifices
    0.06
    Activations Density 0.029%

    No Known Activations