© 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. 28953
    Prev
    Next
    INDEX
    Explanations

    specific book titles and the expression of strong emotions towards fictional characters or elements

    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
    ä½
    -0.07
    æŃ»
    -0.07
     GUIContent
    -0.07
    auer
    -0.07
    ACES
    -0.07
    isku
    -0.07
    iddet
    -0.07
    ģm
    -0.06
    aryawan
    -0.06
    æŃ©
    -0.06
    POSITIVE LOGITS
     Invent
    0.06
     adventure
    0.06
     pals
    0.06
     invent
    0.06
    exampleInputEmail
    0.06
    iff
    0.06
     fast
    0.06
    ansen
    0.06
     FAST
    0.06
    Ñįй
    0.06
    Activations Density 0.011%

    No Known Activations