© 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. 763
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to motion and direction

    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
    ardy
    -0.08
    elize
    -0.07
    erator
    -0.07
    addin
    -0.07
    osta
    -0.07
    Nhap
    -0.07
    olin
    -0.07
     nÃło
    -0.07
    REEN
    -0.07
    oose
    -0.07
    POSITIVE LOGITS
     again
    0.08
     thereof
    0.08
     afterwards
    0.07
    again
    0.07
     ones
    0.07
     later
    0.07
    etur
    0.07
    åıĪ
    0.06
     wieder
    0.06
     thereafter
    0.06
    Activations Density 0.033%

    No Known Activations