© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74926
    Prev
    Next
    INDEX
    Explanations

    references to physical sensations or movements

    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
     Minds
    -0.07
    nave
    -0.07
    ngr
    -0.07
    hsi
    -0.06
     Tape
    -0.06
    pesan
    -0.06
    Ïİ
    -0.06
    rica
    -0.06
    (coder
    -0.06
    .heroku
    -0.06
    POSITIVE LOGITS
     trem
    0.13
     Trem
    0.13
     trembling
    0.12
     shaking
    0.10
     shake
    0.09
     shakes
    0.09
     jitter
    0.08
     stead
    0.08
     qu
    0.07
     shaky
    0.07
    Activations Density 0.011%

    No Known Activations