© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125589
    Prev
    Next
    INDEX
    Explanations

    combinations of commas or other punctuation marks

    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
     skeletons
    -0.06
    nesia
    -0.06
    bitset
    -0.06
    mask
    -0.06
    pire
    -0.06
    hiba
    -0.06
    abit
    -0.06
    ikit
    -0.06
     mask
    -0.06
     wa
    -0.06
    POSITIVE LOGITS
    azo
    0.07
    orget
    0.07
    nek
    0.07
    lod
    0.07
    jec
    0.07
     twin
    0.07
    :UITableView
    0.06
    emax
    0.06
    .onResume
    0.06
    λιο
    0.06
    Activations Density 0.056%

    No Known Activations