© 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. 704
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is" in various contexts, indicating existence or description

    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
    ÙĬÙĪÙĨ
    -0.08
    istra
    -0.08
    rvé
    -0.08
    imits
    -0.07
    urse
    -0.07
    curring
    -0.07
    elor
    -0.07
    arin
    -0.07
    PÅĻÃŃ
    -0.07
     Haley
    -0.07
    POSITIVE LOGITS
    oret
    0.07
     because
    0.07
     showc
    0.07
    838
    0.06
     also
    0.06
     especially
    0.06
     include
    0.06
    oretical
    0.06
    430
    0.06
     Setter
    0.06
    Activations Density 0.029%

    No Known Activations