© 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. 17-LLAMASCOPE-RES-131K
    11. 75970
    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
    abyrin
    -0.08
    ephir
    -0.08
    à¸ļาล
    -0.08
    çĶ
    -0.08
    anness
    -0.07
    orta
    -0.07
    landa
    -0.07
    ewitness
    -0.07
    ñana
    -0.07
    esterday
    -0.07
    POSITIVE LOGITS
     ↵
    0.06
     notable
    0.05
     minor
    0.05
    _construct
    0.05
     Hed
    0.05
     biome
    0.05
     tslint
    0.05
     hol
    0.05
     during
    0.05
     personally
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.