© 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. 17-LLAMASCOPE-RES-131K
    6. 3226
    Prev
    Next
    INDEX
    Explanations

    first-person narrative expressions reflecting personal experiences 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
     kå
    -0.07
    .scalablytyped
    -0.06
    Ĥæķ°
    -0.06
     yanı
    -0.06
    ãİ
    -0.06
     Apostle
    -0.06
    orgh
    -0.06
    edar
    -0.06
    оÑĢаÑı
    -0.06
    /forum
    -0.06
    POSITIVE LOGITS
     only
    0.10
     limited
    0.07
    fy
    0.07
     haven
    0.07
    only
    0.07
     already
    0.07
     originally
    0.06
    modo
    0.06
     didn
    0.06
     never
    0.06
    Activations Density 0.039%

    No Known Activations