© 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. 27221
    Prev
    Next
    INDEX
    Explanations

    expressions related to planning, hope, and future expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     :-↵
    -0.06
     Gro
    -0.06
    èn
    -0.06
    ahn
    -0.06
    odont
    -0.06
    achuset
    -0.06
    rollers
    -0.05
    iers
    -0.05
    irsch
    -0.05
     indeed
    -0.05
    POSITIVE LOGITS
     further
    0.14
     others
    0.13
    others
    0.13
     weitere
    0.12
     weiter
    0.11
     ones
    0.11
    è¿Ľä¸ĢæŃ¥
    0.10
     continue
    0.10
    æĽ´å¤ļ
    0.09
    Further
    0.09
    Activations Density 0.036%

    No Known Activations