© 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. 17228
    Prev
    Next
    INDEX
    Explanations

    references to tourism and travel-related information

    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
    ummer
    -0.06
    _online
    -0.06
    pires
    -0.06
    rotch
    -0.05
    ouch
    -0.05
    ÑĥÑĢÑĭ
    -0.05
    ignet
    -0.05
    anie
    -0.05
    perm
    -0.05
    lub
    -0.05
    POSITIVE LOGITS
     other
    0.10
    other
    0.09
    åħ¶ä»ĸ
    0.09
     otras
    0.08
     autres
    0.08
    vos
    0.08
     altre
    0.08
     åħ¶ä»ĸ
    0.08
     andere
    0.08
     elsewhere
    0.07
    Activations Density 0.009%

    No Known Activations