© 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. 16213
    Prev
    Next
    INDEX
    Explanations

    terms related to digital content casting and technology solutions for user experiences

    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
     Bun
    -0.06
    uw
    -0.06
     sew
    -0.06
    ENO
    -0.06
     gay
    -0.06
     cour
    -0.06
     Campus
    -0.05
    wen
    -0.05
     Ana
    -0.05
     Drum
    -0.05
    POSITIVE LOGITS
    riends
    0.08
    ifle
    0.07
    plib
    0.07
     servi
    0.07
    amba
    0.07
    nection
    0.07
    plex
    0.07
    aiser
    0.07
    yclopedia
    0.07
    acist
    0.07
    Activations Density 0.003%

    No Known Activations