© 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. 126133
    Prev
    Next
    INDEX
    Explanations

    gm

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the Faroese word “Løgmaður” (and its inflected/subword pieces) referring to the prime minister.

    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
    et
    -0.09
    ет
    -0.08
    ret
    -0.07
     tit
    -0.07
     char
    -0.07
    	AT
    -0.07
     textAlign
    -0.07
    	nil
    -0.07
    оба
    -0.07
    Credential
    -0.07
    POSITIVE LOGITS
    pr
    0.08
    gn
    0.08
    fr
    0.08
    tn
    0.08
    tr
    0.08
    bd
    0.08
    TR
    0.07
    n
    0.07
    qn
    0.07
    mn
    0.07
    Activations Density 0.376%

    No Known Activations