© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    references to specific topics or subjects

    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
    ude
    -0.07
    orta
    -0.07
    our
    -0.07
    iciencies
    -0.06
    aby
    -0.06
    ager
    -0.06
    out
    -0.06
    ÑĢовиÑĩ
    -0.06
    hw
    -0.06
    outs
    -0.06
    POSITIVE LOGITS
    starter
    0.09
    æĿIJ
    0.08
    perature
    0.08
    (topic
    0.08
    ylim
    0.08
    matter
    0.08
     matter
    0.07
    -topic
    0.07
     Topic
    0.07
    ography
    0.07
    Activations Density 0.011%

    No Known Activations