© 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. 62420
    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
     modern
    -0.06
     Modern
    -0.05
    265
    -0.05
     never
    -0.05
     Outline
    -0.05
    po
    -0.05
     complex
    -0.05
    let
    -0.05
     er
    -0.05
    392
    -0.05
    POSITIVE LOGITS
    lamaz
    0.09
    ï¼ľ
    0.08
    odash
    0.08
    غط
    0.08
    hei
    0.08
    adoo
    0.08
    DCF
    0.08
    DTD
    0.08
    ungan
    0.08
    egen
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.