© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38804
    Prev
    Next
    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash

    The neuron is keyed to the word “without,” as it appears in the warranty‐disclaimer sections of license headers.

    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
     clumsy
    -0.07
     Dok
    -0.06
     enters
    -0.06
     Baton
    -0.06
     iterating
    -0.06
     MatDialog
    -0.06
     раз
    -0.06
    قلال
    -0.06
     گرفتن
    -0.05
    Active
    -0.05
    POSITIVE LOGITS
     dad
    0.07
    _authenticated
    0.07
    มหานคร
    0.06
    invalid
    0.06
     Without
    0.06
     imprison
    0.06
    ροφορίες
    0.06
     Adolescent
    0.06
    ecx
    0.06
    мя
    0.06
    Activations Density 0.001%

    No Known Activations