Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16490
    Prev
    Next
    INDEX
    Explanations

    transport options and arrangements for travel

    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
    ÙĨداÙĨ
    -0.08
     chứng
    -0.08
    yum
    -0.08
    åĩºåı£
    -0.07
    eczy
    -0.07
    宣
    -0.07
    çĽĸ
    -0.07
    amburger
    -0.07
    иÑĤоÑĢ
    -0.07
    Comparer
    -0.07
    POSITIVE LOGITS
     taxi
    0.11
     cab
    0.11
     taxis
    0.10
     Taxi
    0.10
     Uber
    0.09
     car
    0.09
     tax
    0.08
     lim
    0.08
    Uber
    0.08
    Tax
    0.07
    Activations Density 0.020%

    No Known Activations