© 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. 76051
    Prev
    Next
    INDEX
    Explanations

    references to the Hall of Fame across various contexts

    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
    resse
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
     ÐľÑĥ
    -0.07
    nen
    -0.07
    anguage
    -0.06
    er
    -0.06
    standing
    -0.06
     Äijây
    -0.06
    acer
    -0.06
    stairs
    -0.06
    POSITIVE LOGITS
     induction
    0.08
     Cres
    0.08
    oya
    0.07
    itemid
    0.07
     indu
    0.06
    ably
    0.06
    erty
    0.06
    ruary
    0.06
    postId
    0.06
    strap
    0.06
    Activations Density 0.003%

    No Known Activations