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. 44288
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Virgin"

    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
    ein
    -0.08
    resden
    -0.08
    erro
    -0.08
    DDS
    -0.07
    tors
    -0.07
    cps
    -0.07
    eof
    -0.07
    alet
    -0.07
    eless
    -0.07
    drs
    -0.07
    POSITIVE LOGITS
    ity
    0.13
    ian
    0.12
     Islands
    0.12
    ie
    0.11
    ias
    0.11
     Galactic
    0.11
    ians
    0.10
     Mary
    0.10
     Atlantic
    0.10
    ij
    0.10
    Activations Density 0.004%

    No Known Activations