© 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. 40229
    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
    fern
    -0.06
     POS
    -0.06
     chambers
    -0.06
     chamber
    -0.06
     complicated
    -0.06
     civic
    -0.06
     flatt
    -0.05
     lol
    -0.05
     consecutive
    -0.05
    VC
    -0.05
    POSITIVE LOGITS
    ï¼ł
    0.08
     shootout
    0.07
    oogle
    0.07
    ynthesis
    0.07
    iyel
    0.07
    ngör
    0.07
    ssel
    0.07
    tach
    0.07
    esub
    0.07
    oppel
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.