© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82130
    Prev
    Next
    INDEX
    Explanations

    references to comprehensive assessments and thoroughness in evaluations

    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
    éĥ
    -0.08
    æIJŃ
    -0.06
    ä»ĭ
    -0.06
    ToFit
    -0.06
    дÑĸ
    -0.06
    áce
    -0.06
    leaning
    -0.05
     Äijá»ĭnh
    -0.05
    venient
    -0.05
     poil
    -0.05
    POSITIVE LOGITS
     completeness
    0.08
     covers
    0.08
     thoroughly
    0.07
    ãĥ¼ãĥķ
    0.07
    iple
    0.07
     cover
    0.07
     detail
    0.07
     Cover
    0.07
    çķĻ
    0.07
     anticipated
    0.07
    Activations Density 0.022%

    No Known Activations