© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106187
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and phrases indicating conclusions or summaries

    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
    beros
    -0.07
    zilla
    -0.07
    ubern
    -0.07
    otional
    -0.06
    unning
    -0.06
    rie
    -0.06
    бÑĭ
    -0.06
    óc
    -0.06
     Qu
    -0.06
    eria
    -0.06
    POSITIVE LOGITS
    alk
    0.06
    gart
    0.06
     IHttp
    0.06
    اراÙĨ
    0.06
    vant
    0.06
    esan
    0.06
     Welfare
    0.06
    osta
    0.06
    od
    0.06
    MAC
    0.06
    Activations Density 0.006%

    No Known Activations