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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5324
    Prev
    Next
    INDEX
    Explanations

    mathematical or physical concepts related to angles and vectors

    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
    ãĥĥãĥĦ
    -0.07
    олов
    -0.07
    loff
    -0.07
    radu
    -0.07
    ostringstream
    -0.06
    ezier
    -0.06
    ransition
    -0.06
     lateral
    -0.06
    lant
    -0.06
    phan
    -0.06
    POSITIVE LOGITS
     direction
    0.16
     directions
    0.14
    direction
    0.12
     Directions
    0.12
     axis
    0.11
     Direction
    0.11
     vectors
    0.11
    Direction
    0.10
     axes
    0.10
    æĸ¹åIJij
    0.10
    Activations Density 0.098%

    No Known Activations