© 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. 107965
    Prev
    Next
    INDEX
    Explanations

    inquiries or discussions regarding exploring options or seeking information

    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
    ayers
    -0.07
    .Formatting
    -0.06
    _xor
    -0.06
    TOTYPE
    -0.06
    antine
    -0.06
    ensity
    -0.06
    rior
    -0.06
     lẽ
    -0.06
    Mit
    -0.06
    кеÑĤ
    -0.06
    POSITIVE LOGITS
     possibilities
    0.15
     possibility
    0.15
     possible
    0.12
     possibilit
    0.12
     options
    0.11
     ways
    0.11
     whether
    0.10
     possibile
    0.10
    æĺ¯åIJ¦
    0.10
     возможноÑģÑĤÑĮ
    0.09
    Activations Density 0.025%

    No Known Activations