© 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. 84691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ieu
    -0.08
    _AUTHOR
    -0.07
    atical
    -0.06
    éīĦéģĵ
    -0.06
    gmt
    -0.06
    mist
    -0.06
    hazi
    -0.06
    rahim
    -0.06
    SKU
    -0.06
    IVA
    -0.06
    POSITIVE LOGITS
     extract
    0.06
     Hammond
    0.06
    ourcem
    0.06
    SOC
    0.06
    .toDouble
    0.06
     Coff
    0.06
    WER
    0.06
    biased
    0.06
    rians
    0.06
     Anch
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.