Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96202
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and functions

    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
    inx
    -0.08
    оÑĢÑĸв
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    .strictEqual
    -0.06
     out
    -0.06
    ÑĮÑİ
    -0.06
    òn
    -0.06
    Ù
    -0.06
    loub
    -0.06
    unas
    -0.06
    POSITIVE LOGITS
    azer
    0.07
     Leh
    0.06
    ools
    0.06
    iya
    0.06
    chte
    0.06
    386
    0.06
    ERO
    0.06
    citation
    0.06
    zp
    0.06
    FP
    0.06
    Activations Density 0.000%

    No Known Activations