© 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. 81880
    Prev
    Next
    INDEX
    Explanations

    phrases related to assurance and proper execution of tasks

    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
    addons
    -0.07
    OLON
    -0.07
     Ob
    -0.06
    heck
    -0.06
    aille
    -0.06
    tree
    -0.06
    oba
    -0.06
    cad
    -0.06
    EMU
    -0.06
     cl
    -0.06
    POSITIVE LOGITS
    opsis
    0.07
     Adler
    0.07
     rencont
    0.06
     postup
    0.06
    urch
    0.06
    ãĥ¼ãĥ«
    0.06
     Lone
    0.06
    enor
    0.06
    θι
    0.06
    é¾
    0.06
    Activations Density 0.002%

    No Known Activations