© 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. 29911
    Prev
    Next
    INDEX
    Explanations

    references to additional information and services related to submissions

    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
    celik
    -0.07
    atte
    -0.07
    łģ
    -0.07
    jom
    -0.07
    ajas
    -0.06
    OLUMNS
    -0.06
    ÙĦÙħÙĩ
    -0.06
    _abstract
    -0.06
    zones
    -0.06
    ZONE
    -0.06
    POSITIVE LOGITS
     similar
    0.09
     any
    0.07
     similarly
    0.07
    ANY
    0.06
     reasonably
    0.06
    imilar
    0.06
     unnamed
    0.06
     addition
    0.06
     other
    0.06
     prom
    0.06
    Activations Density 0.018%

    No Known Activations