© 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. 7765
    Prev
    Next
    INDEX
    Explanations

    particle

    np_max-act · gemini-2.0-flash

    The neuron flags code tokens related to particle systems—e.g., “particle,” “particles,” “ParticleSystem,” and similar terminology.

    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
     spherical
    -0.07
    .VAL
    -0.06
     Alabama
    -0.06
    biên
    -0.06
     massively
    -0.06
     Anaheim
    -0.06
    ologically
    -0.06
     Delaware
    -0.06
    Hex
    -0.06
     sharedApplication
    -0.06
    POSITIVE LOGITS
    isLoading
    0.07
    ้จ
    0.07
    xBF
    0.07
    _TRAIN
    0.06
    (Print
    0.06
    @media
    0.06
    �
    0.06
    μιο
    0.06
     getItemCount
    0.06
     ファ
    0.06
    Activations Density 0.013%

    No Known Activations