© 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. 39401
    Prev
    Next
    INDEX
    Explanations

    special characters or diacritical marks in 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
    entin
    -0.08
    aset
    -0.07
    otti
    -0.07
    ÅĻel
    -0.06
    beiter
    -0.06
    apan
    -0.06
     Peek
    -0.06
     GmbH
    -0.06
    heck
    -0.06
    arium
    -0.06
    POSITIVE LOGITS
    s
    0.12
    Ùĩ
    0.08
    istory
    0.08
    sik
    0.07
    sut
    0.07
    udio
    0.07
     latter
    0.07
    olume
    0.07
    ehler
    0.07
    shal
    0.07
    Activations Density 0.021%

    No Known Activations