© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57079
    Prev
    Next
    INDEX
    Explanations

    references to new models or features of vehicles

    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
     ÎļÏħ
    -0.06
    arpa
    -0.06
    å¦
    -0.06
    è¥
    -0.06
    angan
    -0.06
     Union
    -0.05
    ç¼ĺ
    -0.05
    ãģ£ãģ±
    -0.05
     BitSet
    -0.05
    Union
    -0.05
    POSITIVE LOGITS
    rei
    0.08
    version
    0.08
    edl
    0.08
     edition
    0.07
     version
    0.07
     iteration
    0.07
    eten
    0.07
     versions
    0.07
    edition
    0.07
     ?><?
    0.07
    Activations Density 0.009%

    No Known Activations