Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5750
    Prev
    Next
    INDEX
    Explanations

    discussion about focus and attention on various efforts or issues

    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
    kos
    -0.07
    _FC
    -0.07
    opers
    -0.07
    TL
    -0.07
    itere
    -0.07
    زاÙĨ
    -0.07
    jišť
    -0.07
     nederland
    -0.07
    _reference
    -0.07
    _ALWAYS
    -0.07
    POSITIVE LOGITS
     elsewhere
    0.10
     towards
    0.09
     onto
    0.09
     upon
    0.09
     focused
    0.08
     Else
    0.08
    .focus
    0.08
     toward
    0.08
     where
    0.08
     focus
    0.08
    Activations Density 0.013%

    No Known Activations