© 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. 125766
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content and digital formats

    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
    hl
    -0.07
    bris
    -0.06
     Busty
    -0.06
     solic
    -0.06
    .ws
    -0.06
     Studios
    -0.06
    ember
    -0.06
     cref
    -0.06
     boarding
    -0.06
    apg
    -0.06
    POSITIVE LOGITS
    orch
    0.08
    -txt
    0.07
     Preis
    0.07
     bufsize
    0.06
    ]={↵
    0.06
     explan
    0.06
    ãģ£ãģ±
    0.06
    FORMAT
    0.06
     texte
    0.06
    à¸ķร
    0.06
    Activations Density 0.001%

    No Known Activations