© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43249
    Prev
    Next
    INDEX
    Explanations

    reflection

    np_max-act · gemini-2.0-flash

    phrases related to teaching and learning methodologies.

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

    This neuron never activates (all its values are zero), so it doesn’t detect or respond to any pattern.

    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
    /host
    -0.07
     supply
    -0.06
    Ports
    -0.06
    Cheap
    -0.06
     elsewhere
    -0.06
    	MD
    -0.06
     Layout
    -0.06
     Ahmad
    -0.06
    oward
    -0.06
    _r
    -0.06
    POSITIVE LOGITS
     reflective
    0.09
     maduras
    0.08
     addslashes
    0.07
    elpers
    0.07
    ічні
    0.07
    ‐‐
    0.07
    修
    0.07
     избав
    0.07
    664
    0.07
    ouples
    0.06
    Activations Density 0.007%

    No Known Activations