© 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. 57501
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and educational contexts

    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
    виÑĩай
    -0.06
     TREE
    -0.06
    ollo
    -0.06
    æĽ¸
    -0.06
     bes
    -0.06
     unders
    -0.06
     Kil
    -0.06
    jet
    -0.06
    olle
    -0.06
    åģ¶
    -0.06
    POSITIVE LOGITS
    Äįan
    0.07
    ÄĻp
    0.07
    IME
    0.07
    .Restrict
    0.06
     Brewer
    0.06
    DataStream
    0.06
    phin
    0.06
    CEE
    0.06
    ManagedObjectContext
    0.06
    leigh
    0.06
    Activations Density 0.000%

    No Known Activations