© 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. 17-LLAMASCOPE-RES-131K
    11. 86251
    Prev
    Next
    INDEX
    Explanations

    terms related to "pass" 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
    tsy
    -0.09
    pton
    -0.08
    issen
    -0.08
    onth
    -0.07
    Sharper
    -0.07
    pais
    -0.07
    ÑģÑĮ
    -0.07
    indle
    -0.07
    ize
    -0.07
    ãģ¨ãģĵãĤį
    -0.06
    POSITIVE LOGITS
    ionate
    0.11
    (es
    0.11
    enger
    0.11
    engers
    0.11
    aging
    0.10
    code
    0.10
    ively
    0.09
    over
    0.09
    ag
    0.09
    phrase
    0.09
    Activations Density 0.035%

    No Known Activations