© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103659
    Prev
    Next
    INDEX
    Explanations

    brackets or punctuation marks in the text

    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
    ï¼ł
    -0.08
    icari
    -0.08
     Bilim
    -0.08
     strav
    -0.07
    еÑĢе
    -0.07
    StackNavigator
    -0.07
     VAR
    -0.07
    .Microsoft
    -0.07
    bei
    -0.07
    vro
    -0.07
    POSITIVE LOGITS
     personals
    0.06
     McCart
    0.05
     McInt
    0.05
     referring
    0.05
    sten
    0.05
     diss
    0.05
    ä¸ĸç´Ģ
    0.05
    ONENT
    0.05
    imoto
    0.05
    aren
    0.05
    Activations Density 0.000%

    No Known Activations