© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43344
    Prev
    Next
    INDEX
    Explanations

    search queries

    np_max-act · gemini-2.0-flash

    This neuron activates on the words “search” and “queries,” i.e. when the user is asking to generate or list search queries.

    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
    eer
    -0.07
    ельно
    -0.07
     pump
    -0.07
    263
    -0.06
     refine
    -0.06
    wich
    -0.06
    Death
    -0.06
    HE
    -0.06
     grabbed
    -0.06
    Safe
    -0.06
    POSITIVE LOGITS
     BIG
    0.07
    &&(
    0.07
    ็อต
    0.06
    )
    ↵
    ↵
    ↵
    0.06
    .sky
    0.06
     unsub
    0.06
     iod
    0.06
    ManyToOne
    0.06
     теб
    0.06
    willReturn
    0.06
    Activations Density 0.014%

    No Known Activations