© 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. 40628
    Prev
    Next
    INDEX
    Explanations

    technical details and considerations related to computer performance and optimization

    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
    ifr
    -0.09
    Ħĸ
    -0.08
    ilden
    -0.08
    anglicky
    -0.08
    «ĺ
    -0.08
    znik
    -0.07
    ureka
    -0.07
    orre
    -0.07
    Äĥr
    -0.07
    ença
    -0.07
    POSITIVE LOGITS
     opt
    0.08
     consider
    0.07
    cho
    0.07
     Consider
    0.07
     might
    0.07
     Fol
    0.07
     choose
    0.06
    Consider
    0.06
     appropri
    0.06
     best
    0.06
    Activations Density 0.029%

    No Known Activations