© 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. 127140
    Prev
    Next
    INDEX
    Explanations

    references to hotel or reception-related services and areas

    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
    ancias
    -0.07
    lsa
    -0.06
    esc
    -0.06
    PK
    -0.06
    pk
    -0.06
    zug
    -0.06
    zk
    -0.06
    .mit
    -0.06
    -specific
    -0.06
    iego
    -0.06
    POSITIVE LOGITS
    opup
    0.07
    isman
    0.07
    nas
    0.07
     manned
    0.07
    uyá»ĩn
    0.06
     respondsToSelector
    0.06
    _TRANSL
    0.06
     kay
    0.06
     located
    0.06
    omanip
    0.06
    Activations Density 0.020%

    No Known Activations