© 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. 5-LLAMASCOPE-RES-131K
    11. 126469
    Prev
    Next
    INDEX
    Explanations

    references to the nose, including its functions and related medical conditions

    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
    adr
    -0.07
    toa
    -0.07
    hem
    -0.06
    @student
    -0.06
    CursorPosition
    -0.06
     kali
    -0.06
    idan
    -0.06
    antar
    -0.06
    æİ
    -0.06
    ÙĪÙĦÙĬÙĪ
    -0.06
    POSITIVE LOGITS
    gate
    0.08
    sey
    0.07
    DAQ
    0.07
    -tip
    0.07
     Hol
    0.07
    wick
    0.06
    ãģ¾ãģ¾
    0.06
    Hol
    0.06
     hol
    0.06
    IRQ
    0.06
    Activations Density 0.005%

    No Known Activations