© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3868
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or entities related to technology or business

    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
    .jasper
    -0.08
    (=)
    -0.07
    alth
    -0.07
    ζÏĮ
    -0.07
    insky
    -0.07
    afen
    -0.07
    insk
    -0.07
    ofilm
    -0.07
    batim
    -0.07
    adera
    -0.07
    POSITIVE LOGITS
     software
    0.07
     Software
    0.07
    Software
    0.07
     FIXME
    0.06
     code
    0.06
    software
    0.06
     commercial
    0.06
     developer
    0.06
     ara
    0.06
     misplaced
    0.06
    Activations Density 0.043%

    No Known Activations