© 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. 74793
    Prev
    Next
    INDEX
    Explanations

    words related to different shapes and structures in biology

    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
    @dynamic
    -0.06
    skin
    -0.06
    åıįåºĶ
    -0.06
    νÏĮ
    -0.06
    673
    -0.06
     ÑĢок
    -0.06
    prak
    -0.06
    íĬ
    -0.06
     ceremon
    -0.06
    824
    -0.06
    POSITIVE LOGITS
    âĻĢ
    0.07
    Ｌ
    0.06
    uae
    0.06
    issor
    0.06
    rello
    0.06
     Anast
    0.06
    éĹĺ
    0.06
     Luna
    0.06
    ATAB
    0.06
     Broad
    0.06
    Activations Density 0.021%

    No Known Activations