© 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. 92521
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and materials

    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
    å½
    -0.08
    pcm
    -0.07
    mere
    -0.07
    .scalablytyped
    -0.07
    ISCO
    -0.07
    avir
    -0.07
    æ²¹
    -0.07
    ủi
    -0.06
    aminer
    -0.06
    pekt
    -0.06
    POSITIVE LOGITS
    å¦ĥ
    0.07
    اÙģظ
    0.07
     vacancy
    0.06
    Wheel
    0.06
     Kauf
    0.06
    charg
    0.06
    STEM
    0.06
     bou
    0.06
     glasses
    0.06
    wheel
    0.06
    Activations Density 0.024%

    No Known Activations