© 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. 18051
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially those associated with measurements or statistics

    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
    ohana
    -0.07
    æŁ»
    -0.07
     Scarborough
    -0.06
    elson
    -0.06
     Cres
    -0.06
     è±
    -0.06
    ORTH
    -0.06
    OLF
    -0.06
    rend
    -0.06
    okud
    -0.06
    POSITIVE LOGITS
    uset
    0.06
    aux
    0.06
     ########.
    0.06
    uding
    0.06
    afs
    0.06
    ello
    0.06
    zers
    0.06
    liest
    0.05
    hoe
    0.05
    _compat
    0.05
    Activations Density 0.001%

    No Known Activations