© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 89007
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and social perceptions of individuals with disabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammable
    -0.06
    gos
    -0.06
    наÑĢ
    -0.06
    allet
    -0.06
    ông
    -0.06
    nest
    -0.06
    baz
    -0.06
    usto
    -0.06
     vac
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
     accommodation
    0.08
     normal
    0.08
     compens
    0.08
     mainstream
    0.08
     accommodations
    0.08
     disabled
    0.08
     normals
    0.08
     adapted
    0.07
     NORMAL
    0.07
     Disabled
    0.07
    Activations Density 0.008%

    No Known Activations