© 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. 128429
    Prev
    Next
    INDEX
    Explanations

    terms related to suitability and fit for specific applications or conditions

    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
    chen
    -0.07
    ghi
    -0.07
    oad
    -0.07
    pra
    -0.07
    ãĥĹãĥª
    -0.06
    nder
    -0.06
    ion
    -0.06
    ndo
    -0.06
    y
    -0.06
     Å
    -0.06
    POSITIVE LOGITS
     Král
    0.08
     to
    0.07
    éī
    0.07
    say
    0.07
    metis
    0.07
    ëĸ
    0.07
    orst
    0.06
    .inline
    0.06
    aidu
    0.06
    eldo
    0.06
    Activations Density 0.003%

    No Known Activations