© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126266
    Prev
    Next
    INDEX
    Explanations

    spring

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on mentions of the season “spring” (and related time words like “temps”).

    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
     myth
    -0.07
     pall
    -0.06
    erner
    -0.06
    bm
    -0.06
    eras
    -0.06
    Iteration
    -0.06
    iative
    -0.06
     Oy
    -0.06
    atis
    -0.06
     Persistent
    -0.06
    POSITIVE LOGITS
     spring
    0.08
     Trojan
    0.07
    ije
    0.07
     IMessage
    0.06
     Pods
    0.06
     captions
    0.06
    &B
    0.06
    lahoma
    0.06
     περιο
    0.06
    gage
    0.06
    Activations Density 0.017%

    No Known Activations