Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 71249
    Prev
    Next
    INDEX
    Explanations

    actions involving physical retrieval or obtaining objects

    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
    leader
    -0.06
    ADER
    -0.06
    ambre
    -0.06
    GED
    -0.06
     Huffman
    -0.06
    ader
    -0.06
    Leader
    -0.05
     Klo
    -0.05
     fit
    -0.05
    ling
    -0.05
    POSITIVE LOGITS
    ikk
    0.08
    aryl
    0.08
    ubyte
    0.07
     подÑħод
    0.07
    sdk
    0.07
    под
    0.07
    ίαÏĤ
    0.07
    éı¡
    0.07
    ıkl
    0.07
    930
    0.06
    Activations Density 0.021%

    No Known Activations