© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    clinical features and outcomes related to various medical conditions, particularly focusing on diagnosis and prognosis indicators.

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

    The neuron never activates on any tokens—it’s effectively unused and does not detect any particular 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
    κέ
    -0.07
     "\",
    -0.07
    vtk
    -0.06
    ющихся
    -0.06
    istro
    -0.06
    ForRow
    -0.06
     Barr
    -0.06
     ()=>{↵
    -0.06
    irit
    -0.06
    Mocks
    -0.06
    POSITIVE LOGITS
     Tatto
    0.07
     ABOUT
    0.07
     Damn
    0.07
     propiedad
    0.06
     shall
    0.06
     nomin
    0.06
    952
    0.06
     courte
    0.06
     Ave
    0.06
    澤
    0.06
    Activations Density 0.005%

    No Known Activations