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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103693
    Prev
    Next
    INDEX
    Explanations

    statements about the challenges and dynamics of relationships and behavior among individuals

    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
    phinx
    -0.07
    unami
    -0.06
    laus
    -0.06
    æĵļ
    -0.06
    enin
    -0.06
    iated
    -0.06
    .cd
    -0.06
    oge
    -0.06
    CLE
    -0.06
    agr
    -0.06
    POSITIVE LOGITS
     inevitable
    0.09
     occasionally
    0.09
     unavoid
    0.09
     inev
    0.08
     unavoidable
    0.08
     naturally
    0.07
     occasional
    0.07
     inevitably
    0.07
     sometimes
    0.07
     Naturally
    0.07
    Activations Density 0.128%

    No Known Activations