© 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. 83069
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags in the document

    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
    thur
    -0.06
     Linh
    -0.06
    ipes
    -0.06
    zag
    -0.06
     react
    -0.06
    lsa
    -0.06
    inalg
    -0.05
     drag
    -0.05
     LZ
    -0.05
     bis
    -0.05
    POSITIVE LOGITS
    tuk
    0.07
    ¼åIJĪ
    0.06
    avra
    0.06
    /frontend
    0.06
    abra
    0.06
    JECT
    0.06
    /octet
    0.06
     takson
    0.06
    .mj
    0.06
     ******************************************************************************↵
    0.06
    Activations Density 0.000%

    No Known Activations