© 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. 29691
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced computing and neural technologies

    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
     puck
    -0.07
    :relative
    -0.07
    Lint
    -0.06
    akedown
    -0.06
    aoke
    -0.06
    abe
    -0.06
    uarios
    -0.06
    egg
    -0.06
    ething
    -0.06
     authenticated
    -0.06
    POSITIVE LOGITS
    utow
    0.09
     feed
    0.08
     learning
    0.08
     Feed
    0.08
     input
    0.07
    784
    0.07
     networks
    0.07
    /feed
    0.07
     network
    0.07
    ReLU
    0.07
    Activations Density 0.036%

    No Known Activations