© 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. 106271
    Prev
    Next
    INDEX
    Explanations

    programming and API-related concepts, particularly focusing on responses and error codes

    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
    .updateDynamic
    -0.08
    .scalablytyped
    -0.07
     perhaps
    -0.07
    ë³´ì¦Ŀê¸Ī
    -0.07
     diseñador
    -0.07
    ụn
    -0.06
     наÑģÑĤ
    -0.06
     BITTE
    -0.06
    .this
    -0.06
    ê±°ëŀĺê°Ģ
    -0.06
    POSITIVE LOGITS
     correct
    0.07
     bé
    0.06
    PING
    0.06
    383
    0.06
    tle
    0.06
    gado
    0.06
    .':
    0.06
    aley
    0.06
     inh
    0.06
     bol
    0.06
    Activations Density 0.008%

    No Known Activations