© 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. 62002
    Prev
    Next
    INDEX
    Explanations

    descriptors of impressiveness or extraordinary qualities

    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
    apos
    -0.07
    ãĥ³ãĥĩ
    -0.07
    bos
    -0.07
    uzzi
    -0.06
    æľ
    -0.06
    -operator
    -0.06
    zin
    -0.06
    essa
    -0.06
    trinsic
    -0.06
    ÃĸL
    -0.06
    POSITIVE LOGITS
    ingly
    0.14
     amount
    0.12
    ly
    0.12
    LY
    0.11
     amounts
    0.10
    amount
    0.09
    ously
    0.09
     Amount
    0.08
    ably
    0.08
    mente
    0.08
    Activations Density 0.038%

    No Known Activations