© 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. 87673
    Prev
    Next
    INDEX
    Explanations

    negations and phrases related to conclusions or actions taken

    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
    enna
    -0.08
    gone
    -0.07
    anki
    -0.07
    fur
    -0.07
    creativecommons
    -0.06
    achuset
    -0.06
     fur
    -0.06
     ç²
    -0.06
    cia
    -0.06
    posit
    -0.06
    POSITIVE LOGITS
    _si
    0.06
    angan
    0.06
    ãĥ¼ãĥ
    0.06
    -cols
    0.06
    .apps
    0.05
    isons
    0.05
    ãģ¡ãģ¯
    0.05
     Marathon
    0.05
     Swe
    0.05
    tems
    0.05
    Activations Density 0.001%

    No Known Activations