© 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. 128141
    Prev
    Next
    INDEX
    Explanations

    references to technological or procedural developments in various contexts

    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
    -0.06
     Cond
    -0.06
    COND
    -0.06
    ?url
    -0.06
    instanc
    -0.06
     cond
    -0.06
    ULE
    -0.06
    cond
    -0.06
    ãĥ¼ãĥķ
    -0.06
    unma
    -0.06
    POSITIVE LOGITS
     comment
    0.11
     comments
    0.09
    comment
    0.09
     discussion
    0.07
     PageSize
    0.07
     Comment
    0.07
     readers
    0.07
     coment
    0.07
    .comment
    0.07
     commentaire
    0.07
    Activations Density 0.466%

    No Known Activations