© 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. 126721
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    references to educational institutions and their attributes.

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

    The neuron fires on “is a/​is the” copulas that introduce definitions or descriptions of a named entity.

    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
    『
    -0.06
     mined
    -0.06
     Ні
    -0.06
    ゴ
    -0.06
     Luck
    -0.06
    喜
    -0.05
     Bucc
    -0.05
     Вол
    -0.05
     tote
    -0.05
     прос
    -0.05
    POSITIVE LOGITS
    assignment
    0.07
    missing
    0.07
    legation
    0.06
    agens
    0.06
    _POLICY
    0.06
     violation
    0.06
    _patient
    0.06
    FolderPath
    0.06
     mensen
    0.06
     tijd
    0.06
    Activations Density 0.028%

    No Known Activations