© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70746
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate significance or pauses in text

    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
     ApplicationException
    -0.07
    alsy
    -0.07
    ilarity
    -0.07
    elic
    -0.07
    иком
    -0.07
    ãĤ¤ãĥī
    -0.07
    ØŃت
    -0.06
    ã
    -0.06
    _ascii
    -0.06
    _WS
    -0.06
    POSITIVE LOGITS
     etc
    0.09
    /or
    0.07
     which
    0.07
     czy
    0.06
     nor
    0.06
     or
    0.06
     although
    0.06
    etc
    0.06
    ulfilled
    0.05
    .UR
    0.05
    Activations Density 0.048%

    No Known Activations