© 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. 15073
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching for or inquiring about specific resources or solutions

    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
    628
    -0.07
     thai
    -0.06
    ream
    -0.06
    .hu
    -0.06
     storm
    -0.06
    iam
    -0.05
    aper
    -0.05
     Weiner
    -0.05
     burst
    -0.05
    radan
    -0.05
    POSITIVE LOGITS
    _fonts
    0.07
    .DeepEqual
    0.07
     particular
    0.07
    æķ£
    0.07
     nÃło
    0.07
     Salah
    0.07
    specific
    0.07
     GLUT
    0.07
     specific
    0.07
    icode
    0.07
    Activations Density 0.004%

    No Known Activations