© 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. 127091
    Prev
    Next
    INDEX
    Explanations

    Script/play lines

    np_max-act · gemini-2.0-flash

    This neuron activates on parenthesized stage directions or character asides (text enclosed in parentheses).

    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
     empirical
    -0.07
     Quality
    -0.07
    わず
    -0.06
     Clips
    -0.06
     됩니다
    -0.06
     Compensation
    -0.06
     yani
    -0.06
    十五
    -0.06
    なんて
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
     dna
    0.08
    oster
    0.06
    бут
    0.06
     °
    0.06
     immigration
    0.06
     exit
    0.06
    arr
    0.06
    麗
    0.06
    Gen
    0.06
    rypto
    0.06
    Activations Density 0.015%

    No Known Activations