© 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. 45024
    Prev
    Next
    INDEX
    Explanations

    Explanations or Narratives

    np_max-act · gemini-2.0-flash

    phrases related to transactions or agreements.

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

    This neuron fires on the speaker’s self-references to possessions or supplies (e.g. “I have a backpack,” “food,” “tripod,” “videos”).

    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
     obligated
    -0.07
     transforms
    -0.06
    untos
    -0.06
     verse
    -0.06
     Mesh
    -0.06
     Palestinian
    -0.06
    _WATCH
    -0.06
    apter
    -0.06
    _stamp
    -0.06
     combining
    -0.06
    POSITIVE LOGITS
    \C
    0.08
    ',)↵
    0.07
    社区
    0.06
     기
    0.06
    stdClass
    0.06
    olio
    0.06
    (DIR
    0.06
    plor
    0.06
    (va
    0.06
    ящих
    0.06
    Activations Density 0.001%

    No Known Activations