© 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. 29540
    Prev
    Next
    INDEX
    Explanations

    components related to analytics and web development

    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
    .googleapis
    -0.07
    ึ
    -0.07
     Schn
    -0.06
    имв
    -0.06
     veter
    -0.06
    èĻ
    -0.06
    à¹ģà¸Ķà¸ĩ
    -0.06
    æ®
    -0.06
    :\/\/
    -0.06
    urette
    -0.06
    POSITIVE LOGITS
     extra
    0.07
     Petro
    0.06
    oldown
    0.06
     elt
    0.06
    alter
    0.06
    ãĥ¼ãĥł
    0.06
     alter
    0.06
     body
    0.06
    _extra
    0.06
     exceptionally
    0.06
    Activations Density 0.006%

    No Known Activations