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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5389
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seen" and phrases related to experiences or encounters

    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
    XH
    -0.06
     tomorrow
    -0.06
    currently
    -0.06
    å½ĵåīį
    -0.06
    idual
    -0.06
     ÑģейÑĩаÑģ
    -0.06
    ades
    -0.06
     currently
    -0.06
    aan
    -0.06
    urnal
    -0.06
    POSITIVE LOGITS
     anywhere
    0.14
     anybody
    0.10
     ANY
    0.10
     ever
    0.10
     anything
    0.10
     anyone
    0.09
     EVER
    0.09
    Anywhere
    0.09
     any
    0.08
    ANY
    0.08
    Activations Density 0.015%

    No Known Activations