© 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. 15-LLAMASCOPE-RES-131K
    11. 913
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel recommendations and accommodations

    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
    orca
    -0.07
    redient
    -0.06
    PTR
    -0.06
    DOC
    -0.06
    /tos
    -0.06
    -functional
    -0.06
    functional
    -0.06
    enta
    -0.06
    ascus
    -0.06
    üm
    -0.06
    POSITIVE LOGITS
     sling
    0.07
     Shank
    0.07
     Ñĩого
    0.06
     doGet
    0.06
    achs
    0.06
    saldo
    0.06
    ime
    0.06
    ÑĤÑı
    0.06
     Seg
    0.06
     macros
    0.06
    Activations Density 0.002%

    No Known Activations