© 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. 55950
    Prev
    Next
    INDEX
    Explanations

    concepts related to innovative thinking and problem-solving strategies

    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
    umont
    -0.07
    rlen
    -0.07
    ायन
    -0.07
     Pratt
    -0.07
    arna
    -0.07
    DataTask
    -0.07
    pps
    -0.07
    dz
    -0.07
    indr
    -0.06
    apia
    -0.06
    POSITIVE LOGITS
     thinking
    0.16
    thinking
    0.15
    -thinking
    0.14
     Thinking
    0.14
    Thinking
    0.14
     THINK
    0.11
    æĢĿèĢĥ
    0.11
    think
    0.11
     thinks
    0.10
     think
    0.10
    Activations Density 0.076%

    No Known Activations