© 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. 90324
    Prev
    Next
    INDEX
    Explanations

    HTML and styling class attributes within code snippets

    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
    umann
    -0.08
    esa
    -0.07
    strup
    -0.07
    prit
    -0.07
    orsk
    -0.07
    gos
    -0.06
    اÙĤØ©
    -0.06
    Äįel
    -0.06
    UMAN
    -0.06
    wares
    -0.06
    POSITIVE LOGITS
     jadx
    0.08
    ctime
    0.07
     ra
    0.06
    252
    0.06
     Huff
    0.06
    DST
    0.06
    zen
    0.06
    -aligned
    0.06
    æŀľ
    0.05
    Emer
    0.05
    Activations Density 0.000%

    No Known Activations