© 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. 15-LLAMASCOPE-RES-131K
    11. 103844
    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
     &
    -0.07
    756
    -0.05
     regardless
    -0.05
    624
    -0.05
     /
    -0.05
     Doub
    -0.05
    UI
    -0.05
    olic
    -0.05
    hoff
    -0.05
     SF
    -0.05
    POSITIVE LOGITS
    _________________↵↵
    0.09
    รà¸ĵ
    0.08
    _usec
    0.08
    .idea
    0.08
    oggles
    0.08
     çĻ
    0.08
    apis
    0.08
    asurer
    0.08
    algo
    0.08
    lint
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.