© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    themes related to moral conflict and human vices

    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
    chemas
    -0.10
    chema
    -0.09
    ÃĹ↵↵
    -0.08
    anon
    -0.08
    oload
    -0.08
    ertainment
    -0.08
    ABCDEFG
    -0.08
    arel
    -0.08
     Prostitutas
    -0.08
    _Tis
    -0.08
    POSITIVE LOGITS
     ph
    0.06
     multiple
    0.06
     cat
    0.06
     Moran
    0.06
     cul
    0.06
     double
    0.06
     Gre
    0.05
     a
    0.05
     very
    0.05
     briefly
    0.05
    Activations Density 0.022%

    No Known Activations