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. 11474
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "come" and its variations in different tenses

    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
    allas
    -0.09
    abra
    -0.07
    ARP
    -0.06
    verty
    -0.06
    emme
    -0.06
    holm
    -0.06
    .scalablytyped
    -0.06
    ternet
    -0.06
     zi
    -0.06
    .â̦↵↵
    -0.06
    POSITIVE LOGITS
     hot
    0.12
     after
    0.12
     amid
    0.12
     as
    0.11
     despite
    0.11
     amidst
    0.10
     ahead
    0.10
     days
    0.10
     against
    0.10
     weeks
    0.10
    Activations Density 0.008%

    No Known Activations