© 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. 127221
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel arrangements and opportunities

    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
     golf
    -0.07
    sville
    -0.07
     Goldberg
    -0.07
    alion
    -0.07
     Golf
    -0.07
    PROTO
    -0.07
    UFFER
    -0.07
    acks
    -0.07
    inel
    -0.06
     Rocks
    -0.06
    POSITIVE LOGITS
    itar
    0.06
    jal
    0.06
    iggins
    0.06
    ji
    0.06
    jen
    0.05
    033
    0.05
    _Tick
    0.05
    ë´ī
    0.05
     Breaking
    0.05
    iri
    0.05
    Activations Density 0.000%

    No Known Activations