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. 44203
    Prev
    Next
    INDEX
    Explanations

    references to fiscal years and financial-related terms

    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
    aac
    -0.07
    loquent
    -0.06
    aic
    -0.06
    resume
    -0.06
    fusc
    -0.06
     Vinci
    -0.06
     Invocation
    -0.06
    kB
    -0.06
    Accepted
    -0.06
    fony
    -0.06
    POSITIVE LOGITS
     year
    0.11
     cliff
    0.10
     responsibility
    0.09
    -year
    0.08
     years
    0.08
     quarter
    0.08
    ized
    0.08
     Cliff
    0.08
     minded
    0.07
     
    0.07
    Activations Density 0.005%

    No Known Activations