© 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. 84622
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "P" and its variations in reference to academic citations or publications

    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
    aring
    -0.07
    allery
    -0.07
     DropIndex
    -0.07
    ازÙħ
    -0.07
    (Spring
    -0.07
    ará
    -0.07
    rop
    -0.07
    SystemService
    -0.07
    Ã
    -0.07
    erty
    -0.07
    POSITIVE LOGITS
     Tou
    0.07
    g
    0.06
    ож
    0.06
     Lav
    0.06
     minh
    0.06
    ernet
    0.05
     vol
    0.05
    fal
    0.05
     refrain
    0.05
     Six
    0.05
    Activations Density 0.049%

    No Known Activations