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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4230
    Prev
    Next
    INDEX
    Explanations

    numeric values and historical references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
    202
    -0.11
    201
    -0.10
    Û²Û°Û²
    -0.09
    veau
    -0.08
    ðŁĴ
    -0.08
    аÑĢан
    -0.07
    Û²Û°Û±
    -0.07
    -0.07
     ðŁĴ
    -0.07
     Kavanaugh
    -0.07
    POSITIVE LOGITS
    195
    0.10
    196
    0.09
    194
    0.09
    197
    0.08
     Beat
    0.06
    193
    0.06
    à¹ĩà¸Ļà¸Ń
    0.06
     cond
    0.05
    60
    0.05
    Û±Û¹Ûµ
    0.05
    Activations Density 0.054%

    No Known Activations