© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87036
    Prev
    Next
    INDEX
    Explanations

    references to special treatment or favoritism

    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
    kla
    -0.08
    nock
    -0.08
    aeper
    -0.07
    ofire
    -0.07
    znik
    -0.07
    agna
    -0.07
    untas
    -0.07
    å±¥
    -0.07
     å¾Ĵ
    -0.07
    Helmet
    -0.07
    POSITIVE LOGITS
     special
    0.16
     privileges
    0.12
    special
    0.12
    çī¹æ®Ĭ
    0.12
     privilege
    0.11
     treatment
    0.11
     Special
    0.11
     SPECIAL
    0.11
     priority
    0.10
    Special
    0.10
    Activations Density 0.080%

    No Known Activations