© 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. 106238
    Prev
    Next
    INDEX
    Explanations

    opening parentheses in the 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
    ãĥ¬ãĥĥãĥĪ
    -0.08
    using
    -0.07
    asil
    -0.07
    lectic
    -0.06
    _OCCURRED
    -0.06
     Constantin
    -0.06
    arella
    -0.06
    оба
    -0.06
    angelo
    -0.06
    ...">↵
    -0.06
    POSITIVE LOGITS
    oret
    0.07
    jeta
    0.06
    ollo
    0.06
    ÌĨ
    0.06
    cir
    0.06
    adies
    0.06
    imson
    0.06
     ç±
    0.06
     adjud
    0.05
    ì°¸
    0.05
    Activations Density 0.022%

    No Known Activations