© 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. 55734
    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
    bian
    -0.06
     Hud
    -0.06
     "
    -0.06
     ways
    -0.05
     house
    -0.05
     ‘
    -0.05
     p
    -0.05
     `
    -0.05
    olith
    -0.05
     our
    -0.05
    POSITIVE LOGITS
    seau
    0.09
    лага
    0.08
    asso
    0.08
    éł
    0.08
    ÑģÑĤан
    0.08
    ãĤ·ãĥ¼
    0.08
    .sb
    0.08
    taxonomy
    0.08
    FFFFFFFF
    0.08
     tabPage
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.