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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61287
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to programming and data 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
    /slick
    -0.07
    zell
    -0.06
    imos
    -0.06
     sacr
    -0.06
    ::
    -0.06
    ueil
    -0.06
    /src
    -0.06
    IFEST
    -0.06
    emmel
    -0.06
     Perl
    -0.06
    POSITIVE LOGITS
    GINE
    0.08
    alet
    0.07
     Elias
    0.07
    =default
    0.07
    oppel
    0.07
    byname
    0.07
    ;↵↵
    0.06
    ãĥ¼ãĥĨãĤ£
    0.06
    asename
    0.06
    .LA
    0.06
    Activations Density 0.053%

    No Known Activations