© 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. 83191
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and their associated items or features

    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
    WARDED
    -0.06
     Kale
    -0.06
    ilor
    -0.06
    951
    -0.06
    ::.
    -0.05
    ì¹
    -0.05
    agli
    -0.05
    cript
    -0.05
    Vien
    -0.05
    /Branch
    -0.05
    POSITIVE LOGITS
     ----------------------------------------------------------------------------↵
    0.07
    istrovstvÃŃ
    0.07
    evin
    0.07
    ropolitan
    0.07
     konkrét
    0.07
    frey
    0.07
    ork
    0.07
     cra
    0.06
    ogan
    0.06
    ourcem
    0.06
    Activations Density 0.001%

    No Known Activations