© 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. 22-LLAMASCOPE-RES-131K
    6. 4207
    Prev
    Next
    INDEX
    Explanations

    locations and transport connections between cities

    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
     Pond
    -0.07
     pond
    -0.07
     Rivers
    -0.07
    utm
    -0.06
    lemetry
    -0.06
     lake
    -0.06
     Welt
    -0.06
     Lake
    -0.06
     Guth
    -0.06
    pond
    -0.06
    POSITIVE LOGITS
     cliff
    0.10
     cliffs
    0.08
     Cornwall
    0.08
     Cliff
    0.08
     viewpoints
    0.07
     prom
    0.07
    )))),
    0.07
     UNESCO
    0.07
     Hubb
    0.07
     Patron
    0.07
    Activations Density 0.001%

    No Known Activations