© 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. 70870
    Prev
    Next
    INDEX
    Explanations

    terms related to naming and categorization

    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
    isku
    -0.07
    воÑĢ
    -0.07
    edom
    -0.07
    deniz
    -0.07
    GGLE
    -0.07
    _FW
    -0.06
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.06
     tinh
    -0.06
    .Reporting
    -0.06
    ãĥĸãĥ«
    -0.06
    POSITIVE LOGITS
    ival
    0.07
    utive
    0.06
    kazy
    0.06
    {{{
    0.06
     Lage
    0.06
    eps
    0.06
    t
    0.06
    ivial
    0.06
    bare
    0.06
    ined
    0.06
    Activations Density 0.001%

    No Known Activations