© 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. 94337
    Prev
    Next
    INDEX
    Explanations

    key topics or themes mentioned in the document

    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
    kur
    -0.06
     cr
    -0.06
     ow
    -0.06
     &
    -0.06
    arme
    -0.06
     fresh
    -0.05
     cannabis
    -0.05
     Turnbull
    -0.05
    anse
    -0.05
    illy
    -0.05
    POSITIVE LOGITS
     Harm
    0.07
    Äįin
    0.07
     tá»ĩ
    0.07
    ANTLR
    0.07
    ormal
    0.07
    ushima
    0.07
    itsu
    0.07
    ropa
    0.07
    igram
    0.07
    åłĨ
    0.07
    Activations Density 0.000%

    No Known Activations