© 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. 71163
    Prev
    Next
    INDEX
    Explanations

    instances of noteworthy punctuation or formatting in text

    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
    áÄį
    -0.07
    OwnerId
    -0.07
    برÛĮ
    -0.07
     Karlov
    -0.07
    ele
    -0.07
    arie
    -0.06
    ResourceId
    -0.06
    ulton
    -0.06
    ildo
    -0.06
    ilda
    -0.06
    POSITIVE LOGITS
     frost
    0.06
     mar
    0.06
    kem
    0.06
    ONY
    0.06
    kp
    0.06
    IRC
    0.06
    eny
    0.05
    Coder
    0.05
     feedback
    0.05
     Gala
    0.05
    Activations Density 0.000%

    No Known Activations