© 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. 61644
    Prev
    Next
    INDEX
    Explanations

    terms related to forces and mechanical properties

    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
    ugg
    -0.08
    åĪĩãĤĬ
    -0.06
    atched
    -0.06
     hacks
    -0.06
     hacked
    -0.06
    ediator
    -0.06
    alse
    -0.06
    atti
    -0.06
    ardon
    -0.06
    ital
    -0.06
    POSITIVE LOGITS
    -force
    0.10
    Strength
    0.09
     force
    0.09
     Forces
    0.09
    forces
    0.09
     forces
    0.09
     Strength
    0.08
     Force
    0.08
    åĬĽ
    0.08
    (force
    0.08
    Activations Density 0.026%

    No Known Activations