© 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. 5211
    Prev
    Next
    INDEX
    Explanations

    details about fishing and marine life

    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
     batches
    -0.07
     shm
    -0.07
    554
    -0.06
    inka
    -0.06
    itten
    -0.06
    833
    -0.06
    878
    -0.06
     опÑĤим
    -0.06
    791
    -0.06
    ipple
    -0.06
    POSITIVE LOGITS
     Pes
    0.07
    eum
    0.06
    omentum
    0.06
     keeper
    0.06
     cork
    0.06
    amics
    0.06
     téc
    0.06
     Backbone
    0.06
     motion
    0.05
    ASSES
    0.05
    Activations Density 0.004%

    No Known Activations