© 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. 126014
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals, particularly regarding their feelings or opinions

    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
    ÙĪرا
    -0.07
    avou
    -0.07
    ingu
    -0.07
    iden
    -0.06
    oblin
    -0.06
    oksen
    -0.06
     Bard
    -0.06
    aras
    -0.06
     Glow
    -0.06
    laps
    -0.06
    POSITIVE LOGITS
    ervo
    0.08
     Weiss
    0.06
     Mods
    0.06
    é¨
    0.06
    peek
    0.06
    instruction
    0.06
    apo
    0.05
     reb
    0.05
     DateTimeKind
    0.05
     Pocket
    0.05
    Activations Density 0.009%

    No Known Activations