© 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. 5121
    Prev
    Next
    INDEX
    Explanations

    phrases indicating improvement or facilitation in processes or experiences

    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
    olin
    -0.06
    adium
    -0.06
    arf
    -0.06
    eor
    -0.06
    uble
    -0.06
    ixo
    -0.06
    abin
    -0.06
    gings
    -0.06
    pend
    -0.06
    cope
    -0.06
    POSITIVE LOGITS
    ë¶
    0.07
    asso
    0.07
    asured
    0.07
    ackson
    0.07
    ang
    0.07
    ao
    0.06
    allows
    0.06
    nev
    0.06
    autop
    0.06
    .Async
    0.06
    Activations Density 0.015%

    No Known Activations