© 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. 75141
    Prev
    Next
    INDEX
    Explanations

    numerical values and terms related to biological or physical processes and 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
    sez
    -0.09
    åIJįçĦ¡ãģĹ
    -0.08
    ба
    -0.07
     dán
    -0.07
    croft
    -0.07
    /libs
    -0.07
    .scalablytyped
    -0.07
    xes
    -0.07
    imli
    -0.07
    SEE
    -0.07
    POSITIVE LOGITS
     alike
    0.07
    ign
    0.06
    ateg
    0.06
     é
    0.05
    fm
    0.05
     Fate
    0.05
    acular
    0.05
     ÙħعÙĦÙĪÙħات
    0.05
    iling
    0.05
    igit
    0.05
    Activations Density 0.034%

    No Known Activations