© 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. 127628
    Prev
    Next
    INDEX
    Explanations

    structures or amenities associated with travel and tourism

    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
    roke
    -0.07
     based
    -0.06
     audio
    -0.06
    ãģĶãģĸ
    -0.05
     distributed
    -0.05
    onde
    -0.05
    ied
    -0.05
     Elliott
    -0.05
    vs
    -0.05
     Version
    -0.05
    POSITIVE LOGITS
    izzle
    0.09
    má
    0.09
    lém
    0.08
    REEN
    0.08
    ritel
    0.08
    eyen
    0.08
    evin
    0.08
    emmel
    0.08
    detail
    0.07
    Detail
    0.07
    Activations Density 0.001%

    No Known Activations