© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87891
    Prev
    Next
    INDEX
    Explanations

    events involving animals

    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
    thouse
    -0.07
     tick
    -0.07
    å°İ
    -0.06
    ÑĢаж
    -0.06
    Ñī
    -0.06
    indow
    -0.06
    umbs
    -0.06
     embr
    -0.06
    биÑĤ
    -0.06
    703
    -0.06
    POSITIVE LOGITS
     approached
    0.09
     approach
    0.08
     approaching
    0.08
    appro
    0.08
     Approach
    0.07
     подой
    0.07
     beck
    0.07
     walked
    0.07
    bbe
    0.07
     appro
    0.06
    Activations Density 0.023%

    No Known Activations