© 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. 71467
    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
    ube
    -0.07
    holm
    -0.07
    uran
    -0.07
    avy
    -0.06
    odi
    -0.06
    ,'#
    -0.06
    ORK
    -0.06
    posables
    -0.06
    ÑĥÑħ
    -0.06
    DITION
    -0.06
    POSITIVE LOGITS
    CHIP
    0.08
    .scalablytyped
    0.08
    feof
    0.07
     Chick
    0.06
    obil
    0.06
    _redirect
    0.06
    Chip
    0.06
    chip
    0.06
     imprison
    0.06
     chÄĥm
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.