© 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. 87195
    Prev
    Next
    INDEX
    Explanations

    phrases indicating commitment or dedication to a cause or activity

    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
    .bundle
    -0.07
    EI
    -0.07
    ERM
    -0.07
    urum
    -0.07
    окол
    -0.07
    γγ
    -0.07
    åŀ
    -0.07
    istol
    -0.06
    ]][
    -0.06
    ulse
    -0.06
    POSITIVE LOGITS
     time
    0.08
     effort
    0.08
     devoted
    0.07
     attention
    0.07
     efforts
    0.07
     resources
    0.07
    /dev
    0.06
     Ded
    0.06
     energies
    0.06
     considerable
    0.06
    Activations Density 0.006%

    No Known Activations