© 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. 58503
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "first" or primary positions in various contexts

    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
    steen
    -0.07
    urator
    -0.06
    opot
    -0.06
    ointed
    -0.06
    est
    -0.06
    -Version
    -0.06
    orman
    -0.06
    ardu
    -0.06
     hWnd
    -0.06
    -legged
    -0.06
    POSITIVE LOGITS
    uelle
    0.07
    -of
    0.07
    idor
    0.07
    borg
    0.06
    495
    0.06
    ffe
    0.06
    aux
    0.06
    ÅĻeb
    0.06
    ียà¸Ķ
    0.06
    uet
    0.06
    Activations Density 0.023%

    No Known Activations