© 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. 71080
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an error or invalid action

    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
     absent
    -0.06
     gran
    -0.06
    üml
    -0.05
    olen
    -0.05
     baby
    -0.05
     Gran
    -0.05
     Walters
    -0.05
    ythe
    -0.05
     el
    -0.05
    -0.05
    POSITIVE LOGITS
    redo
    0.08
    LETTE
    0.08
     ìĭ¤í
    0.08
    APON
    0.08
     Äijá»Ļng
    0.07
    IDI
    0.07
    UTTON
    0.07
    igor
    0.07
    iore
    0.07
    è¯Ĭ
    0.07
    Activations Density 0.001%

    No Known Activations