© 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. 92209
    Prev
    Next
    INDEX
    Explanations

    Advocacy/Campaigns

    np_max-act · gemini-2.0-flash

    The neuron activates on action words that denote taking up a cause or helping others (e.g. verbs like “decided,” “make,” “spread,” “advocate,” “help,” “work”).

    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
     embraced
    -0.06
    ności
    -0.06
     lắng
    -0.06
    uess
    -0.06
    .depend
    -0.06
    MASK
    -0.06
    MV
    -0.06
     reimburse
    -0.06
    SI
    -0.06
    _SN
    -0.06
    POSITIVE LOGITS
     arisen
    0.07
     timeStamp
    0.06
     induced
    0.06
    ुद
    0.06
     Ethan
    0.06
    ριο
    0.06
    ура
    0.06
    .ObjectId
    0.06
    enzyme
    0.06
     Durant
    0.06
    Activations Density 0.012%

    No Known Activations