© 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. 15-LLAMASCOPE-RES-131K
    11. 1140
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly colons and dashes

    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
     Broker
    -0.06
    cn
    -0.06
     Schneider
    -0.05
    k
    -0.05
    odos
    -0.05
    ie
    -0.05
     Bart
    -0.05
     subject
    -0.05
     unlimited
    -0.05
     Toll
    -0.05
    POSITIVE LOGITS
    ÑĩаÑģ
    0.08
    à¥ľà¤ķ
    0.08
    ãİ
    0.08
     cocci
    0.08
    AFX
    0.08
    #__
    0.08
    #ad
    0.08
    ì§Ģë§ī
    0.08
     Pazar
    0.07
    .IContainer
    0.07
    Activations Density 0.000%

    No Known Activations