© 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 EvalsExportsAPI 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. 88379
    Prev
    Next
    INDEX
    Explanations

    instances of structured value definitions or declarations within a programming context

    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
    umber
    -0.09
    like
    -0.09
    ly
    -0.08
    lan
    -0.08
    mens
    -0.08
    la
    -0.08
    lik
    -0.08
    li
    -0.07
    avec
    -0.07
    ega
    -0.07
    POSITIVE LOGITS
    -added
    0.09
    fully
    0.09
    lessness
    0.08
    entin
    0.08
    lessly
    0.08
    less
    0.08
    holder
    0.07
    åŁŁ
    0.07
    -nil
    0.07
    guard
    0.07
    Activations Density 0.053%

    No Known Activations