© 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. 78083
    Prev
    Next
    INDEX
    Explanations

    concepts related to the development and articulation of ideas and obstacles in creative processes

    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
    ona
    -0.07
    ê³³
    -0.06
    ÏģιÏĥ
    -0.06
    inus
    -0.06
    Č
    -0.06
     Dit
    -0.06
    /browse
    -0.06
    خط
    -0.06
    338
    -0.05
     Wak
    -0.05
    POSITIVE LOGITS
    ë¦
    0.07
    ancybox
    0.07
    ç¼ĺ
    0.07
    egie
    0.07
    è
    0.06
     kıs
    0.06
     tzv
    0.06
     essentially
    0.06
    odies
    0.06
    NOP
    0.06
    Activations Density 0.105%

    No Known Activations