© 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. 42726
    Prev
    Next
    INDEX
    Explanations

    Peru

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the country “Peru” (and related Peruvian place names).

    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
    лл
    -0.07
     Prec
    -0.07
    again
    -0.07
    “All
    -0.07
    )\↵
    -0.06
    "]).
    -0.06
    ]|
    -0.06
     jue
    -0.06
     Kobe
    -0.06
    "At
    -0.06
    POSITIVE LOGITS
    riding
    0.07
     peru
    0.07
     infect
    0.07
     USING
    0.06
    (config
    0.06
     требуется
    0.06
     Reads
    0.06
    Repair
    0.06
    .Clear
    0.06
    NF
    0.06
    Activations Density 0.014%

    No Known Activations