© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or sentiments

    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
    ermen
    -0.07
    izik
    -0.07
    abay
    -0.07
    ritable
    -0.07
    hta
    -0.07
    monds
    -0.07
    gren
    -0.07
    ubre
    -0.07
    ipur
    -0.06
    _DETECT
    -0.06
    POSITIVE LOGITS
    lessly
    0.08
     Aires
    0.08
    ao
    0.07
    bil
    0.07
     rằng
    0.07
     дека
    0.07
    /generated
    0.06
    less
    0.06
    chine
    0.06
    -Allow
    0.06
    Activations Density 0.005%

    No Known Activations