© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106980
    Prev
    Next
    INDEX
    Explanations

    references to time periods or breaks in activity, particularly related to "bye" weeks and voting abstentions

    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
    Jar
    -0.07
    iane
    -0.06
    iership
    -0.06
    vero
    -0.06
    rrha
    -0.06
     WRONG
    -0.06
    icari
    -0.06
    vern
    -0.06
     fran
    -0.06
    жÑĥ
    -0.06
    POSITIVE LOGITS
    931
    0.08
    /null
    0.06
    åıĤåĬł
    0.06
    .nlm
    0.06
     Σε
    0.06
     rather
    0.06
    imest
    0.06
     inher
    0.06
     upon
    0.06
     participation
    0.06
    Activations Density 0.013%

    No Known Activations