© 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. 22-LLAMASCOPE-RES-131K
    6. 4232
    Prev
    Next
    INDEX
    Explanations

    themes of betrayal and conflict

    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
     Fulton
    -0.07
    æķı
    -0.07
    uant
    -0.07
     Snyder
    -0.07
    rani
    -0.06
    pend
    -0.06
     Lyons
    -0.06
     TCHAR
    -0.06
    dete
    -0.06
    æī¬
    -0.06
    POSITIVE LOGITS
     Mid
    0.07
     Num
    0.07
     Aaron
    0.07
     Wilderness
    0.07
     calf
    0.06
     ISR
    0.06
     Numbers
    0.06
     Utah
    0.06
     Caleb
    0.06
    Kansas
    0.06
    Activations Density 0.000%

    No Known Activations