© 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. 73893
    Prev
    Next
    INDEX
    Explanations

    Changes in circumstances

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on abstract “pivot” words that signal a shift or turning point in the narrative (e.g. hope, fate, weather, point, dust).

    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
    =value
    -0.08
     Hub
    -0.06
     Льв
    -0.06
    =find
    -0.06
     troubleshooting
    -0.06
     گفت
    -0.06
     Attr
    -0.06
     irradi
    -0.06
    уска
    -0.06
    ursions
    -0.06
    POSITIVE LOGITS
     fantas
    0.07
    uxt
    0.07
     अप
    0.06
     ac
    0.06
     caso
    0.06
    _eof
    0.06
     past
    0.06
     sums
    0.06
     tijd
    0.06
     dank
    0.06
    Activations Density 0.126%

    No Known Activations