© 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. 87989
    Prev
    Next
    INDEX
    Explanations

    important dates and times

    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
    Äĥn
    -0.06
     Finn
    -0.06
    -type
    -0.06
    agr
    -0.06
    arel
    -0.06
    rain
    -0.06
     Wool
    -0.06
     wool
    -0.06
    avery
    -0.05
    TypeInfo
    -0.05
    POSITIVE LOGITS
    ystack
    0.07
    eyh
    0.07
    -preview
    0.07
    cheng
    0.07
    "crypto
    0.07
    ntax
    0.07
    StackNavigator
    0.07
    ежаÑĤÑĮ
    0.06
    uitka
    0.06
    /../
    0.06
    Activations Density 0.007%

    No Known Activations