© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4460
    Prev
    Next
    INDEX
    Explanations

    terms related to adventure sports, particularly skydiving

    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
    ledo
    -0.07
    MK
    -0.06
     Brill
    -0.06
    iven
    -0.06
    orsi
    -0.06
    LT
    -0.06
    otti
    -0.06
    ñana
    -0.06
    ffic
    -0.05
    lder
    -0.05
    POSITIVE LOGITS
    çĢ¬
    0.08
    dü
    0.08
    DataContract
    0.07
     Virgin
    0.07
     flight
    0.07
    avaÅŁ
    0.07
    anton
    0.07
     Wings
    0.07
    mund
    0.06
     Hick
    0.06
    Activations Density 0.005%

    No Known Activations