© 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. 17-LLAMASCOPE-RES-131K
    11. 77509
    Prev
    Next
    INDEX
    Explanations

    instances of the word "De."

    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
    oust
    -0.08
    eru
    -0.07
    ra
    -0.07
    fir
    -0.07
    pus
    -0.07
    fire
    -0.07
    elier
    -0.07
    ro
    -0.07
    rous
    -0.07
    dated
    -0.07
    POSITIVE LOGITS
    acon
    0.08
    žel
    0.07
    oxy
    0.07
    anship
    0.07
    construct
    0.07
     facto
    0.07
    asil
    0.07
     la
    0.06
    ák
    0.06
    eds
    0.06
    Activations Density 0.047%

    No Known Activations