© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89908
    Prev
    Next
    INDEX
    Explanations

    Earning money

    np_max-act · gemini-2.0-flash

    The neuron detects and highlights mentions of monetary amounts (numbers paired with currencies).

    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
     tuberculosis
    -0.07
     TripAdvisor
    -0.06
     Şimdi
    -0.06
    -feedback
    -0.06
     kapsamında
    -0.06
     Calendar
    -0.06
    _SR
    -0.06
    .Slice
    -0.06
     Pickup
    -0.06
    	elem
    -0.06
    POSITIVE LOGITS
     счита
    0.07
     учит
    0.07
    icina
    0.06
     corpor
    0.06
    杜
    0.06
     pickle
    0.06
    discard
    0.06
    Analy
    0.06
    CKER
    0.06
    quarters
    0.06
    Activations Density 0.025%

    No Known Activations