© 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. 97575
    Prev
    Next
    INDEX
    Explanations

    references to geological surveys and mapping information

    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
    ase
    -0.06
     Ka
    -0.06
    isible
    -0.06
    arters
    -0.06
    .ibm
    -0.06
    ems
    -0.06
     ka
    -0.05
     Sem
    -0.05
    anning
    -0.05
    ocation
    -0.05
    POSITIVE LOGITS
    'gc
    0.10
    кÑĥл
    0.09
    ÛĮÛĮÙĨ
    0.08
     tÃŃ
    0.08
    ovÃŃ
    0.08
    _sdk
    0.07
    /Gate
    0.07
    ãĥ³ãĥĸ
    0.07
    ãģĹãĤĩ
    0.07
    SSIP
    0.07
    Activations Density 0.022%

    No Known Activations