© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73643
    Prev
    Next
    INDEX
    Explanations

    secondary

    np_max-act · gemini-2.0-flash

    medical terminology related to rare conditions and their diagnoses.

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

    This neuron primarily responds to occurrences of the word “secondary.”

    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
    rock
    -0.07
     cable
    -0.06
     FileWriter
    -0.06
    漢
    -0.06
     Balt
    -0.06
    Consult
    -0.06
     video
    -0.06
    udas
    -0.06
    _radius
    -0.06
     attitude
    -0.06
    POSITIVE LOGITS
    serviceName
    0.07
    _ROUND
    0.07
    生
    0.06
     logits
    0.06
     muchos
    0.06
    SC
    0.06
     иск
    0.06
    [sub
    0.06
    [child
    0.06
     obr
    0.06
    Activations Density 0.006%

    No Known Activations