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. 44197
    Prev
    Next
    INDEX
    Explanations

    symbols and characters representing encoding errors or data corruption

    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
    ritel
    -0.05
    ULO
    -0.05
     Unblock
    -0.05
    tdown
    -0.05
     analyzer
    -0.05
    apiro
    -0.05
    มà¸ķ
    -0.05
    rtl
    -0.05
     fertilizer
    -0.05
    ัà¹Ī
    -0.05
    POSITIVE LOGITS
     militar
    0.11
     Scouts
    0.10
     recruiters
    0.10
     recruitment
    0.09
     youths
    0.09
     kids
    0.09
     recruiter
    0.09
     recruits
    0.09
     recruiting
    0.09
     youth
    0.09
    Activations Density 0.002%

    No Known Activations