© 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. 57486
    Prev
    Next
    INDEX
    Explanations

    references to individual identity and personal connections

    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
     CHARSET
    -0.07
    indered
    -0.07
    kowski
    -0.06
    ouis
    -0.06
    amic
    -0.06
    otten
    -0.06
    noon
    -0.06
    æİĽ
    -0.06
    imbus
    -0.06
     tot
    -0.06
    POSITIVE LOGITS
    SELF
    0.07
    zelf
    0.07
    aday
    0.06
    hunt
    0.06
    ivan
    0.06
    NÄ°
    0.06
    rown
    0.06
     alone
    0.06
    ÏĦÏİ
    0.06
    zz
    0.06
    Activations Density 0.032%

    No Known Activations