© 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. 83013
    Prev
    Next
    INDEX
    Explanations

    specific terms related to data management and technology

    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
    uki
    -0.09
    cene
    -0.08
    ноÑĪ
    -0.08
    iyi
    -0.07
    μή
    -0.07
    oland
    -0.07
    otation
    -0.07
    егоÑĢ
    -0.07
    ::$_
    -0.06
    iid
    -0.06
    POSITIVE LOGITS
    edBy
    0.09
    misc
    0.07
    ologically
    0.06
     Angiospermae
    0.06
    depend
    0.06
     Uns
    0.06
     Magn
    0.06
    ynchronously
    0.06
    äge
    0.06
    nip
    0.06
    Activations Density 0.108%

    No Known Activations