© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76087
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers and self-descriptions concerning personal identity and involvement

    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
    itial
    -0.08
    ceph
    -0.07
    ettel
    -0.07
    NL
    -0.07
     cuckold
    -0.07
    eper
    -0.07
    Ãłm
    -0.07
    æķ¢
    -0.07
    foon
    -0.07
    acie
    -0.07
    POSITIVE LOGITS
     nor
    0.10
     experts
    0.07
     expert
    0.07
    robot
    0.07
     rocket
    0.06
     Anch
    0.06
    rys
    0.06
     anch
    0.06
     Nor
    0.06
     experienced
    0.06
    Activations Density 0.013%

    No Known Activations