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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 87440
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure indicators in a text

    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
     Flood
    -0.07
    stash
    -0.07
    otal
    -0.06
    essel
    -0.06
    ryptography
    -0.06
     floods
    -0.06
    ½æķ°
    -0.06
    umber
    -0.06
    ÏĦον
    -0.06
    å¹
    -0.06
    POSITIVE LOGITS
     slur
    0.07
     kostenlose
    0.07
    .www
    0.07
     Preston
    0.06
    etti
    0.06
    ernaut
    0.06
    arov
    0.06
     kostenlos
    0.06
    tdown
    0.06
     grátis
    0.06
    Activations Density 0.000%

    No Known Activations