© 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. 87455
    Prev
    Next
    INDEX
    Explanations

    specific time indicators or timestamps 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
    asel
    -0.07
    ãĥijãĥ³
    -0.07
    ocz
    -0.06
    ccak
    -0.06
    ÏĦεÏħ
    -0.06
    lett
    -0.06
    thouse
    -0.06
     Colbert
    -0.06
    oren
    -0.06
    $MESS
    -0.06
    POSITIVE LOGITS
    chap
    0.07
    ercul
    0.06
    ampo
    0.06
     Kund
    0.06
    azo
    0.06
    Unnamed
    0.06
     Bout
    0.06
    ocument
    0.06
     chap
    0.05
    ì±Ħ
    0.05
    Activations Density 0.001%

    No Known Activations