© 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. 15-LLAMASCOPE-RES-131K
    11. 1039
    Prev
    Next
    INDEX
    Explanations

    expressions of optimism or desire for positive outcomes

    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
    cki
    -0.08
    adele
    -0.07
    rame
    -0.07
    .ScrollBars
    -0.07
    æĬĢ
    -0.07
    .cx
    -0.07
     Sporting
    -0.07
    lix
    -0.07
    porno
    -0.06
    kinson
    -0.06
    POSITIVE LOGITS
    fs
    0.06
    a
    0.06
    ulo
    0.06
     Peters
    0.06
    udic
    0.05
    unate
    0.05
    bst
    0.05
    æ·
    0.05
    nez
    0.05
     explo
    0.05
    Activations Density 0.000%

    No Known Activations