© 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. 29305
    Prev
    Next
    INDEX
    Explanations

    configurations related to software setup

    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
    aż
    -0.07
    èĶµ
    -0.07
    ÑĽ
    -0.07
     ÑģÑĤоÑĢонÑĥ
    -0.07
    λα
    -0.06
    PageRoute
    -0.06
    æ³ķ人
    -0.06
    CLS
    -0.06
     ÑĢаÐ
    -0.06
     اÙĦسÙĦاÙħ
    -0.06
    POSITIVE LOGITS
     configparser
    0.08
     conf
    0.07
    Ini
    0.07
     Ini
    0.07
    IOC
    0.07
    读
    0.07
     IConfiguration
    0.07
     Sections
    0.06
     Lines
    0.06
    errick
    0.06
    Activations Density 0.078%

    No Known Activations