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. 11496
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to confidentiality and access to documents

    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
    orce
    -0.07
    ools
    -0.07
    pekt
    -0.07
    otre
    -0.06
    оÑģÑĢед
    -0.06
    _magic
    -0.06
    .Stderr
    -0.06
    Ïħνα
    -0.06
    idunt
    -0.06
    orton
    -0.06
    POSITIVE LOGITS
     red
    0.12
     exemptions
    0.12
     exemption
    0.11
     exempt
    0.11
     withheld
    0.11
     withhold
    0.11
     withholding
    0.10
     disclosure
    0.09
     commercial
    0.09
     confidential
    0.09
    Activations Density 0.020%

    No Known Activations