© 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. 55048
    Prev
    Next
    INDEX
    Explanations

    sentences that contain significant statements or claims

    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
    agos
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.07
    AGO
    -0.07
    ago
    -0.06
    anguard
    -0.06
     flock
    -0.05
     printable
    -0.05
     exceptions
    -0.05
     booth
    -0.05
    aha
    -0.05
    POSITIVE LOGITS
    oka
    0.07
    wayne
    0.07
    ез
    0.07
    à¸ļà¸Ĺ
    0.07
    çĶŁ
    0.07
    \OptionsResolver
    0.07
    hower
    0.07
    ť
    0.07
    ÏĦÏģ
    0.07
    .TIM
    0.07
    Activations Density 0.010%

    No Known Activations