© 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. 56394
    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
     Evet
    -0.09
    ould
    -0.08
    uyu
    -0.07
    reon
    -0.07
    efon
    -0.07
    cé
    -0.07
     pec
    -0.07
    ë³µ
    -0.07
    TODO
    -0.07
    eming
    -0.07
    POSITIVE LOGITS
    ÑĢаÑĤ
    0.07
     &
    0.06
     du
    0.06
    obel
    0.06
    adin
    0.06
    ijk
    0.06
    isin
    0.06
    quan
    0.06
    amo
    0.06
     franch
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.