© 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. 89982
    Prev
    Next
    INDEX
    Explanations

    bibliographic and citation information in academic references

    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
     Rh
    -0.06
     Fel
    -0.06
    paralle
    -0.06
     Cath
    -0.06
    ereg
    -0.06
    ارÙģ
    -0.06
    apel
    -0.06
    Äįer
    -0.06
     defer
    -0.06
     пок
    -0.06
    POSITIVE LOGITS
    çĽĺ
    0.08
    缤
    0.06
    íĿ¬
    0.06
    ¼
    0.06
    ees
    0.06
    ee
    0.06
     rebel
    0.06
    orbit
    0.06
    ç¯ĩ
    0.06
    DebugEnabled
    0.06
    Activations Density 0.004%

    No Known Activations