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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43693
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols commonly associated with specific contexts or mathematical expressions

    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
    è£ģ
    -0.07
     seperate
    -0.07
    (EX
    -0.06
     kì
    -0.06
     terrific
    -0.06
    gan
    -0.06
     bicy
    -0.06
    åĶ®
    -0.06
    ิà¸į
    -0.06
    jang
    -0.06
    POSITIVE LOGITS
     terminal
    0.09
     consultation
    0.08
     terminals
    0.08
     navigation
    0.07
     Terminal
    0.07
     :↵
    0.07
    Terminal
    0.07
     ;↵
    0.07
    terminal
    0.07
     consulted
    0.07
    Activations Density 0.004%

    No Known Activations