© 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. 128720
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and venue names

    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
    addChild
    -0.07
     Jako
    -0.07
     lô
    -0.07
    bsp
    -0.07
    amarin
    -0.07
    halt
    -0.07
    andelier
    -0.07
    ãĤ¾
    -0.07
     tamp
    -0.07
    utomation
    -0.07
    POSITIVE LOGITS
    orer
    0.06
    opper
    0.06
    725
    0.06
    č↵č↵č↵č↵
    0.06
    verse
    0.06
    <br
    0.06
    als
    0.06
    ulary
    0.05
    atten
    0.05
    548
    0.05
    Activations Density 0.021%

    No Known Activations