© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119533
    Prev
    Next
    INDEX
    Explanations

    names and terms related to locations, establishments, and organizations

    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
    âĢ¦↵
    -0.06
     Sporting
    -0.06
     Hof
    -0.06
     Ago
    -0.06
    ptic
    -0.05
     âĢ¦↵
    -0.05
     Stern
    -0.05
    ataka
    -0.05
     arr
    -0.05
    ournals
    -0.05
    POSITIVE LOGITS
     nackte
    0.08
    undy
    0.07
    ÅĻeba
    0.07
    .fromFunction
    0.07
    ires
    0.07
    	throws
    0.07
    (())↵
    0.07
    _TAC
    0.07
    és
    0.07
     lesbi
    0.07
    Activations Density 0.012%

    No Known Activations