© 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. 108827
    Prev
    Next
    INDEX
    Explanations

    97

    np_max-act · gemini-2.0-flash

    The neuron activates on the “Action:” instruction lines—especially the token “the” in the phrase “Action: the action to take…” that marks which tool or step to execute.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    commands related to installing software using a terminal interface.

    oai_token-act-pair · gpt-4o-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
    주세요
    -0.06
    posite
    -0.06
     �
    -0.06
     VF
    -0.06
    žil
    -0.06
     Nylon
    -0.06
     сто
    -0.06
    stddef
    -0.06
     juven
    -0.06
     squarely
    -0.06
    POSITIVE LOGITS
    _years
    0.07
    _FAMILY
    0.07
    Years
    0.07
     forControlEvents
    0.06
     incorporating
    0.06
    	Log
    0.06
    -not
    0.06
    [--
    0.06
    acro
    0.06
     combines
    0.06
    Activations Density 0.000%

    No Known Activations