© 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. 15-LLAMASCOPE-RES-131K
    11. 87469
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific methods and processes

    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
    asco
    -0.08
    ãĥĨãĥ«
    -0.08
    reater
    -0.07
    rade
    -0.07
    asar
    -0.07
    ecast
    -0.07
    .consume
    -0.07
     Linh
    -0.07
     AttributeSet
    -0.07
    xmm
    -0.07
    POSITIVE LOGITS
    Mono
    0.06
     reader
    0.06
    Disposition
    0.06
    ning
    0.06
    ↵
    0.05
    olicit
    0.05
    eing
    0.05
    ido
    0.05
    ov
    0.05
     forward
    0.05
    Activations Density 0.000%

    No Known Activations