© 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. 81898
    Prev
    Next
    INDEX
    Explanations

    concepts related to community, resources, and socioeconomic factors

    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
    ancock
    -0.08
    аниÑĨ
    -0.08
    herits
    -0.07
    chied
    -0.07
     Alman
    -0.06
    odyn
    -0.06
    à¸ĵà¸ij
    -0.06
    iley
    -0.06
     recep
    -0.06
    ksi
    -0.06
    POSITIVE LOGITS
     orient
    0.07
    )
    0.06
    istique
    0.06
    ernal
    0.06
    agen
    0.06
    isque
    0.06
     pedig
    0.06
     Stam
    0.06
    ánh
    0.06
    ISTA
    0.06
    Activations Density 0.054%

    No Known Activations