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. 43633
    Prev
    Next
    INDEX
    Explanations

    elements related to societal and ethical issues

    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
    ÎIJ
    -0.07
    okus
    -0.07
    elow
    -0.07
    dfd
    -0.07
    afd
    -0.06
    REA
    -0.06
    angu
    -0.06
    epend
    -0.06
    olly
    -0.06
    izr
    -0.06
    POSITIVE LOGITS
     acquire
    0.23
     acquiring
    0.20
     assume
    0.19
     acquired
    0.19
     assumes
    0.18
     assumed
    0.17
     assuming
    0.16
     acquisition
    0.16
     ac
    0.16
     assum
    0.15
    Activations Density 0.083%

    No Known Activations