© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78750
    Prev
    Next
    INDEX
    Explanations

    references to accommodations and hostels

    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
     golf
    -0.07
     Getty
    -0.07
    ẫu
    -0.06
    Ìģt
    -0.06
     Grat
    -0.06
    .linkedin
    -0.06
     Sutton
    -0.06
    Venue
    -0.06
    Getty
    -0.06
    POSITIVE LOGITS
     hostel
    0.10
     Backpack
    0.09
     backpack
    0.09
     dorm
    0.08
     Host
    0.07
    terminal
    0.07
     travellers
    0.06
    screens
    0.06
     Doyle
    0.06
     communal
    0.06
    Activations Density 0.010%

    No Known Activations