© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38886
    Prev
    Next
    INDEX
    Explanations

    actions in a process

    np_max-act · gemini-2.0-flash

    discussions surrounding environmentally friendly and sustainable practices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is primarily triggered by verbs of movement or transition (e.g. “go,” “goes,” “into,” “through”).

    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
    iet
    -0.07
    iltr
    -0.06
     coleg
    -0.06
     τον
    -0.06
     turn
    -0.06
    ovation
    -0.06
    externalActionCode
    -0.06
    컬
    -0.06
    ix
    -0.06
     ure
    -0.06
    POSITIVE LOGITS
    .getChild
    0.07
    ('',
    0.07
     (*)(
    0.07
     greenhouse
    0.06
    \xaa
    0.06
     आए
    0.06
     захист
    0.06
     nomine
    0.06
    .getWorld
    0.06
    :focus
    0.06
    Activations Density 0.179%

    No Known Activations