© 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. 14792
    Prev
    Next
    INDEX
    Explanations

    file paths or URLs related to content uploads

    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
    coon
    -0.08
    vailability
    -0.08
    Äįit
    -0.08
    oro
    -0.08
    ogl
    -0.07
    porto
    -0.07
    екÑĤоÑĢа
    -0.07
    urdy
    -0.07
    are
    -0.07
    ibal
    -0.07
    POSITIVE LOGITS
    /cop
    0.07
    ãĥ¡ãĥ³ãĥĪ
    0.07
    201
    0.06
     ’
    0.06
    ê¶ģ
    0.06
     hel
    0.06
     Hos
    0.06
    Https
    0.06
    202
    0.06
    'gc
    0.06
    Activations Density 0.004%

    No Known Activations