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. 43563
    Prev
    Next
    INDEX
    Explanations

    references to the name "Paul"

    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
    eyn
    -0.08
     jadx
    -0.07
    ections
    -0.07
    eya
    -0.07
    elper
    -0.07
    ragen
    -0.07
    edback
    -0.07
    efs
    -0.07
    eve
    -0.07
    emachine
    -0.07
    POSITIVE LOGITS
    ine
    0.20
    sen
    0.17
    ina
    0.15
    inus
    0.15
    s
    0.14
    ino
    0.14
    ding
    0.13
    us
    0.13
    ines
    0.12
    ista
    0.12
    Activations Density 0.017%

    No Known Activations