Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29132
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events

    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
     Chennai
    -0.07
     Scarborough
    -0.07
     Sheffield
    -0.07
    isque
    -0.07
     Blackburn
    -0.07
     Eston
    -0.07
     Detroit
    -0.06
    caled
    -0.06
     Nissan
    -0.06
     Tamil
    -0.06
    POSITIVE LOGITS
     Austrian
    0.15
     Vienna
    0.14
     Austria
    0.14
     Avust
    0.11
    Vi
    0.11
    ustria
    0.10
    sterreich
    0.10
     Wien
    0.10
     Vi
    0.09
     Maryland
    0.08
    Activations Density 0.070%

    No Known Activations