© 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. 17-LLAMASCOPE-RES-131K
    11. 76914
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to software development and troubleshooting

    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
    -caret
    -0.07
    ãģ§ãģĹãĤĩãģĨ
    -0.07
     ëĭ¹ìĭł
    -0.07
    Âłtom
    -0.06
     ÑģÑħод
    -0.06
    ResourceId
    -0.06
    UniqueId
    -0.06
     ваÑģ
    -0.06
     Paren
    -0.06
     may
    -0.06
    POSITIVE LOGITS
    boru
    0.09
     بÙĪد
    0.07
    nila
    0.07
    ilon
    0.07
     wasn
    0.07
     jsem
    0.07
    ÅĤem
    0.07
     was
    0.07
    usta
    0.07
     myself
    0.06
    Activations Density 0.010%

    No Known Activations