© 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. 73945
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and presence 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
    unj
    -0.07
    )\<
    -0.07
    ipop
    -0.07
    ago
    -0.07
    iyan
    -0.07
    .local
    -0.06
    hw
    -0.06
    local
    -0.06
    надлеж
    -0.06
    ahl
    -0.06
    POSITIVE LOGITS
     during
    0.16
    during
    0.13
     During
    0.13
     durante
    0.12
    During
    0.11
     bÄĽhem
    0.09
     während
    0.08
     tijd
    0.08
     напÑĢи
    0.08
     at
    0.07
    Activations Density 0.022%

    No Known Activations