© 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. 128753
    Prev
    Next
    INDEX
    Explanations

    AssemblyTrademark

    np_max-act · gemini-2.0-flash

    metadata related to software assembly attributes.

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

    The neuron activates on the numeric trademark version value in assembly metadata (the decimal following the AssemblyTrademark attribute).

    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
     invokevirtual
    -0.06
    373
    -0.06
    .enums
    -0.06
    @Column
    -0.06
     Suzuki
    -0.06
     karma
    -0.06
    cury
    -0.06
    14
    -0.06
    [u
    -0.06
     έχουν
    -0.06
    POSITIVE LOGITS
     AssemblyTrademark
    0.15
    leted
    0.07
    _mark
    0.06
     बढ
    0.06
     espan
    0.06
    èles
    0.06
     PdfPCell
    0.06
    ंध
    0.06
     身
    0.06
     Орг
    0.06
    Activations Density 0.000%

    No Known Activations