© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107140
    Prev
    Next
    INDEX
    Explanations

    references to data and its organization

    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
    ýš
    -0.06
     Strauss
    -0.06
     мол
    -0.06
    onis
    -0.06
    覧
    -0.06
     Parr
    -0.06
     buck
    -0.06
     organ
    -0.06
    èŃ
    -0.06
    806
    -0.06
    POSITIVE LOGITS
    enef
    0.08
    enic
    0.07
    taj
    0.07
    theid
    0.07
    zers
    0.06
    affles
    0.06
    ourd
    0.06
    erras
    0.06
    sap
    0.06
    ɵ
    0.06
    Activations Density 0.001%

    No Known Activations