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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 95486
    Prev
    Next
    INDEX
    Explanations

    references to changes or differences in situations or conditions

    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
    agem
    -0.06
    oeff
    -0.06
     cứ
    -0.06
    ожд
    -0.06
    ospace
    -0.06
    ást
    -0.06
    ëģ¼
    -0.06
     INS
    -0.06
    nell
    -0.06
    (CharSequence
    -0.06
    POSITIVE LOGITS
     changed
    0.14
     changes
    0.13
     change
    0.12
    changed
    0.12
    changes
    0.11
    change
    0.11
     Changes
    0.11
     differently
    0.10
     Changed
    0.10
    Changes
    0.10
    Activations Density 0.078%

    No Known Activations