© 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. 44368
    Prev
    Next
    INDEX
    Explanations

    Commas and parenthesis

    np_max-act · gemini-2.0-flash

    phrases related to materials and their properties, specifically in the context of environmental or medical applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of scientific material‐characterization methods and instruments (e.g. SEM, XRD, FTIR, BET).

    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
    okers
    -0.08
    -0.07
     PDF
    -0.07
     Brady
    -0.06
    FONT
    -0.06
    conditionally
    -0.06
     되는
    -0.06
    Bubble
    -0.06
     IF
    -0.06
    Independent
    -0.06
    POSITIVE LOGITS
    :host
    0.07
    /business
    0.07
     marin
    0.07
     Begins
    0.06
     vå
    0.06
     MessageBoxIcon
    0.06
     LENGTH
    0.06
     HTMLElement
    0.06
     Rt
    0.06
     Investig
    0.06
    Activations Density 0.015%

    No Known Activations