© 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. 84496
    Prev
    Next
    INDEX
    Explanations

    phrases indicating composition or structure

    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
    ipay
    -0.09
    åľŃ
    -0.09
    ipherals
    -0.08
    raud
    -0.08
    ebi
    -0.08
    posables
    -0.08
    /respond
    -0.07
    å¼¾
    -0.07
    iges
    -0.07
     Campos
    -0.07
    POSITIVE LOGITS
     two
    0.11
     three
    0.09
     a
    0.09
     several
    0.08
     fewer
    0.07
     components
    0.07
    two
    0.07
     elements
    0.07
     four
    0.07
    0.07
    Activations Density 0.029%

    No Known Activations