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. 44049
    Prev
    Next
    INDEX
    Explanations

    technical symbols or characters often used in equations 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
    [â̦
    -0.07
    â̦the
    -0.07
     `{
    -0.07
    ).</
    -0.06
    your
    -0.06
    /{{
    -0.06
    &apos
    -0.06
    [_
    -0.06
    \<
    -0.06
    ?</
    -0.06
    POSITIVE LOGITS
     
    0.09
     and
    0.08
     -
    0.08
     literature
    0.07
    ↵
    0.07
     tion
    0.07
     ...↵
    0.07
     journal
    0.07
    ,
    0.07
     -↵
    0.07
    Activations Density 0.004%

    No Known Activations