© 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. 128575
    Prev
    Next
    INDEX
    Explanations

    references to various forms of media and communication technologies

    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
    undler
    -0.08
    æĹħ
    -0.08
    panse
    -0.07
    uien
    -0.07
    Directions
    -0.07
    ordion
    -0.07
    leans
    -0.07
    림
    -0.07
    Ø®ÙĪاÙĨ
    -0.07
    avra
    -0.07
    POSITIVE LOGITS
     versions
    0.07
     amounts
    0.06
     links
    0.06
     copies
    0.06
    imir
    0.06
    opies
    0.06
     solutions
    0.06
    312
    0.06
    insky
    0.06
    umb
    0.05
    Activations Density 0.070%

    No Known Activations