© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56429
    Prev
    Next
    INDEX
    Explanations

    references to travel logistics and destinations

    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
    ksi
    -0.07
     Hu
    -0.07
    atem
    -0.07
    æĬ
    -0.07
    ÑĤÑı
    -0.06
     nhân
    -0.06
     flirting
    -0.06
    425
    -0.06
     leider
    -0.06
    Hu
    -0.06
    POSITIVE LOGITS
    idal
    0.07
    ATUS
    0.07
    lah
    0.06
    imdi
    0.06
    endor
    0.06
    AME
    0.06
    CDATA
    0.06
     pol
    0.06
    oke
    0.06
     vis
    0.06
    Activations Density 0.001%

    No Known Activations