© 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. 73755
    Prev
    Next
    INDEX
    Explanations

    Landmarks and geographical locations

    np_max-act · gemini-2.0-flash

    This neuron fires on phrases asking for the world’s tallest mountain (e.g., “tallest mountain in the world” or variants).

    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
    HD
    -0.07
     flag
    -0.07
    _modified
    -0.07
     Metrics
    -0.07
     Flag
    -0.07
     White
    -0.07
     piece
    -0.07
    	cell
    -0.06
     Corp
    -0.06
    .is
    -0.06
    POSITIVE LOGITS
    >↵↵↵↵
    0.06
    paragraph
    0.06
     перева
    0.06
    aysia
    0.06
     başk
    0.06
     полож
    0.06
    /calendar
    0.06
    τι
    0.06
    세요
    0.06
    三个
    0.06
    Activations Density 0.015%

    No Known Activations