© 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. 92359
    Prev
    Next
    INDEX
    Explanations

    references to the word "Tiger" in various contexts

    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
    imer
    -0.08
    orative
    -0.07
    zier
    -0.07
    utters
    -0.07
    ellite
    -0.07
    elling
    -0.07
    ts
    -0.06
    кÑĢа
    -0.06
    imers
    -0.06
    exampleModal
    -0.06
    POSITIVE LOGITS
    zsche
    0.08
    isay
    0.08
    ial
    0.08
    eview
    0.07
    unning
    0.07
    gram
    0.07
    iana
    0.07
    pio
    0.07
    apult
    0.07
    hawk
    0.07
    Activations Density 0.004%

    No Known Activations