© 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. 15-LLAMASCOPE-RES-131K
    11. 61686
    Prev
    Next
    INDEX
    Explanations

    expressions of personal emotions and familial relationships

    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
    obre
    -0.07
    .pet
    -0.07
    ú
    -0.07
    hek
    -0.07
    ά
    -0.06
    IPH
    -0.06
    IfExists
    -0.06
     podpor
    -0.06
    rale
    -0.06
    aly
    -0.06
    POSITIVE LOGITS
    erp
    0.07
    ãĥĭãĤ¢
    0.06
    ption
    0.06
    _asm
    0.06
    irut
    0.06
     extortion
    0.06
     vice
    0.06
     school
    0.06
     Pent
    0.06
    gart
    0.05
    Activations Density 0.007%

    No Known Activations