© 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. 6905
    Prev
    Next
    INDEX
    Explanations

    exercitation

    np_max-act · gemini-2.0-flash

    The neuron activates on “Lorem ipsum” filler text words (the common Latin-derived tokens used as placeholders).

    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
     brokers
    -0.06
     tol
    -0.06
    您
    -0.06
     variations
    -0.06
     المح
    -0.06
     tel
    -0.06
     business
    -0.06
     Het
    -0.06
    -image
    -0.06
    Lord
    -0.06
    POSITIVE LOGITS
     exercitation
    0.09
    uciones
    0.07
    .rd
    0.07
    """
↵
↵
    0.06
    ัตว
    0.06
     sdl
    0.06
    ibbon
    0.06
    艦
    0.06
    HEADER
    0.06
     Coordinates
    0.06
    Activations Density 0.001%

    No Known Activations