© 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. 61388
    Prev
    Next
    INDEX
    Explanations

    mentions of small or specific items

    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
    uler
    -0.07
    åº
    -0.07
     misd
    -0.07
    orman
    -0.07
    ìŀIJë£Į
    -0.07
    icester
    -0.07
    æ°
    -0.06
    imos
    -0.06
    ican
    -0.06
     themselves
    -0.06
    POSITIVE LOGITS
     my
    0.08
     saya
    0.07
     @
    0.07
    ebek
    0.06
    ãĥ¥ãĥ¼
    0.06
    vil
    0.06
    lick
    0.06
     locally
    0.06
     last
    0.06
     myself
    0.06
    Activations Density 0.069%

    No Known Activations