© 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. 9-LLAMASCOPE-RES-131K
    11. 95711
    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
     Peters
    -0.06
     Cald
    -0.06
    ¤¤
    -0.06
    ricks
    -0.06
    ¤
    -0.06
    ADOR
    -0.06
    XX
    -0.06
    lan
    -0.06
    igers
    -0.06
    iesel
    -0.05
    POSITIVE LOGITS
    ÙģاÙĤ
    0.07
    .scalablytyped
    0.07
    ampp
    0.07
    åįļçī©
    0.06
    kud
    0.06
     Seamless
    0.06
    achable
    0.06
     законодаÑĤелÑĮ
    0.06
    jer
    0.06
    erate
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.