© 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. 39465
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "string" 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
    ignum
    -0.09
    etur
    -0.07
    pig
    -0.07
    ливий
    -0.07
    igue
    -0.07
    quin
    -0.07
    isers
    -0.07
    ÅĻik
    -0.07
    uale
    -0.07
    .UnitTesting
    -0.07
    POSITIVE LOGITS
    795
    0.09
    .fromCharCode
    0.09
    sWith
    0.09
    y
    0.08
    ency
    0.08
    796
    0.08
    ently
    0.07
    enses
    0.07
    ulated
    0.07
    uth
    0.07
    Activations Density 0.009%

    No Known Activations