© 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. 9-LLAMASCOPE-RES-131K
    11. 97609
    Prev
    Next
    INDEX
    Explanations

    URLs and web domains

    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
    ooter
    -0.07
    oss
    -0.07
    æĶ¯
    -0.06
    èn
    -0.06
    æĴŃ
    -0.06
     Garr
    -0.06
    ASM
    -0.06
     enr
    -0.06
     Propel
    -0.06
    988
    -0.06
    POSITIVE LOGITS
     Arth
    0.06
    _ATOMIC
    0.06
    ulent
    0.06
    á»ijn
    0.06
    <Type
    0.06
    ónico
    0.06
     diam
    0.06
    ylv
    0.06
    ÙģØ´
    0.06
    .Cond
    0.06
    Activations Density 0.000%

    No Known Activations