© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82761
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to positioning and seating arrangements

    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
    itchen
    -0.07
    IONS
    -0.07
    .chk
    -0.07
    avn
    -0.07
    ascar
    -0.06
    orris
    -0.06
    اختÙĩ
    -0.06
    åĩºãģĹ
    -0.06
    +len
    -0.06
    _PAGES
    -0.06
    POSITIVE LOGITS
    :
    0.06
     members
    0.06
     left
    0.06
     bench
    0.06
    0.06
    543
    0.05
     Cleanup
    0.05
    urity
    0.05
    lic
    0.05
     transport
    0.05
    Activations Density 0.002%

    No Known Activations