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. 106633
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    eps
    -0.07
    oil
    -0.07
    BitConverter
    -0.06
    å¶
    -0.06
    oly
    -0.06
    _allocate
    -0.06
    KIT
    -0.06
    RAINT
    -0.06
     -*-č↵
    -0.06
    æĹĹ
    -0.06
    POSITIVE LOGITS
     Rim
    0.07
     punishment
    0.07
    è¼Ķ
    0.06
     иÑģ
    0.06
     Pun
    0.06
    वर
    0.06
    dale
    0.06
    inker
    0.06
     Freder
    0.06
    erto
    0.06
    Activations Density 0.000%

    No Known Activations