© 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. 15-LLAMASCOPE-RES-131K
    11. 89829
    Prev
    Next
    INDEX
    Explanations

    the presence of credits or authorship attributions in documents

    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
    ipzig
    -0.06
    ovich
    -0.06
    ips
    -0.06
    adlo
    -0.06
    .googleapis
    -0.06
    abra
    -0.06
     Literary
    -0.06
    aneous
    -0.06
    inte
    -0.06
    ip
    -0.06
    POSITIVE LOGITS
    ilha
    0.07
    dna
    0.07
    presso
    0.07
    ãĥ³ãĥķ
    0.07
     Lean
    0.07
     Hemp
    0.06
    efon
    0.06
     Lon
    0.06
    ôme
    0.06
    çĢ¬
    0.06
    Activations Density 0.004%

    No Known Activations