© 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. 94145
    Prev
    Next
    INDEX
    Explanations

    references to online resources and links

    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
    IPHER
    -0.07
    blr
    -0.07
    ause
    -0.07
    locker
    -0.07
     Leban
    -0.07
    indi
    -0.07
    ÙĪرÙĩ
    -0.07
    ipher
    -0.07
    pdata
    -0.07
    fir
    -0.07
    POSITIVE LOGITS
     Wikipedia
    0.08
     semi
    0.07
     Bart
    0.06
     partly
    0.06
     wikipedia
    0.06
     stub
    0.06
     enc
    0.06
    /wiki
    0.06
     "
    0.06
    .struct
    0.06
    Activations Density 0.003%

    No Known Activations