© 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. 55812
    Prev
    Next
    INDEX
    Explanations

    references to connections and linking between concepts or entities

    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
    tero
    -0.07
    aben
    -0.07
    eel
    -0.06
    strup
    -0.06
     Alvarez
    -0.06
    ulas
    -0.06
    ader
    -0.06
    à¹Ĥà¸Ĺ
    -0.06
    iw
    -0.06
    zer
    -0.06
    POSITIVE LOGITS
    .link
    0.08
    via
    0.07
    /link
    0.07
    hurst
    0.07
    emia
    0.07
    .Link
    0.07
    -linked
    0.07
    (Link
    0.07
    -chain
    0.07
    elves
    0.07
    Activations Density 0.008%

    No Known Activations