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. 43443
    Prev
    Next
    INDEX
    Explanations

    terms related to secrecy and covert operations

    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
    alet
    -0.09
    ovu
    -0.08
    owitz
    -0.08
    erli
    -0.07
    ansas
    -0.07
    itches
    -0.07
    ativa
    -0.07
    evenodd
    -0.07
    ÑģÑĤÑĢов
    -0.06
    ATIONAL
    -0.06
    POSITIVE LOGITS
    inely
    0.16
    ine
    0.13
    itious
    0.10
    inity
    0.10
    inite
    0.09
     operation
    0.09
    uous
    0.09
    INE
    0.08
     operatives
    0.08
    ous
    0.08
    Activations Density 0.004%

    No Known Activations