© 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. 40174
    Prev
    Next
    INDEX
    Explanations

    words related to measurement or dimensions

    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
    bens
    -0.07
    kea
    -0.07
    entimes
    -0.07
    atron
    -0.07
    oth
    -0.07
    vanished
    -0.07
    uster
    -0.07
    jours
    -0.06
    ters
    -0.06
    ech
    -0.06
    POSITIVE LOGITS
     Saw
    0.07
    yne
    0.07
    SCO
    0.07
    network
    0.06
    essen
    0.06
    .foundation
    0.06
     network
    0.06
    emax
    0.06
     saw
    0.06
    hek
    0.06
    Activations Density 0.000%

    No Known Activations