© 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. 56406
    Prev
    Next
    INDEX
    Explanations

    elements related to travel itineraries and tour options

    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
    morgan
    -0.07
     Ley
    -0.07
    uben
    -0.06
    į¼
    -0.06
    alus
    -0.06
    noc
    -0.06
    inspace
    -0.06
    инкÑĥ
    -0.06
    Ñįй
    -0.06
    anooga
    -0.06
    POSITIVE LOGITS
    gle
    0.08
    gel
    0.07
    jong
    0.06
    -series
    0.06
     Pent
    0.06
    zh
    0.06
     downstream
    0.06
    ritt
    0.06
    격
    0.06
     Pace
    0.06
    Activations Density 0.009%

    No Known Activations