© 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. 57165
    Prev
    Next
    INDEX
    Explanations

    importance

    np_max-act · gemini-2.0-flash

    processes related to tax-exempt status and nonprofit organizations.

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

    This neuron activates on introductory hedging or disclaimer phrases that emphasize an important point.

    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
     conoc
    -0.07
    Won
    -0.06
    ODY
    -0.06
     zví
    -0.06
     shar
    -0.05
    433
    -0.05
     coward
    -0.05
     تهیه
    -0.05
     Fantasy
    -0.05
    	channel
    -0.05
    POSITIVE LOGITS
    hexdigest
    0.07
    .</
    0.07
     Mont
    0.07
    (extension
    0.07
    _outline
    0.07
    рест
    0.07
    ?></
    0.07
     Sigma
    0.07
     Beled
    0.07
    .lookup
    0.07
    Activations Density 0.052%

    No Known Activations