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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106413
    Prev
    Next
    INDEX
    Explanations

    organizational entities and companies

    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
    asurer
    -0.10
    PÅĻi
    -0.08
    öff
    -0.08
    éĺħ读次æķ°
    -0.08
    iliki
    -0.08
    Ñħов
    -0.08
    lamaz
    -0.08
    PÅĻed
    -0.08
    ucci
    -0.08
    вÑĸ
    -0.08
    POSITIVE LOGITS
     Inc
    0.09
     r
    0.06
     Division
    0.06
     division
    0.06
    l
    0.06
    Inc
    0.06
    _inc
    0.05
     MOR
    0.05
    LL
    0.05
     T
    0.05
    Activations Density 0.019%

    No Known Activations