© 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 EvalsExportsinterp-engineNEWAPI 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. 107765
    Prev
    Next
    INDEX
    Explanations

    concepts related to disability support and mental health advocacy

    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
    uko
    -0.07
    anni
    -0.06
     Bubble
    -0.06
     id
    -0.06
     Bulk
    -0.06
     disorders
    -0.06
     bulk
    -0.06
     Mult
    -0.06
     Lum
    -0.06
     Cooperative
    -0.05
    POSITIVE LOGITS
    Independ
    0.12
     Independence
    0.11
     independence
    0.10
     independ
    0.09
     Independ
    0.08
    ipc
    0.08
    ÑĥÑĩа
    0.08
     employment
    0.08
     emploi
    0.07
     participation
    0.07
    Activations Density 0.010%

    No Known Activations