© 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 EvalsExportsinterp-engineNEWAPI 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. 116763
    Prev
    Next
    INDEX
    Explanations

    phrases of congratulations and recognition for achievements

    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
    оÑģÑĤаÑĤ
    -0.07
    rops
    -0.07
    umin
    -0.06
    osti
    -0.06
    ear
    -0.06
    oplan
    -0.06
    fred
    -0.06
    uman
    -0.06
    ondo
    -0.06
    _into
    -0.06
    POSITIVE LOGITS
    uele
    0.06
    602
    0.06
    datatable
    0.06
    ì§ľ
    0.06
    ếu
    0.06
    ìĭĿìĿĦ
    0.06
     wherever
    0.06
     Walt
    0.06
    itis
    0.06
    lah
    0.06
    Activations Density 0.005%

    No Known Activations