© 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. 106323
    Prev
    Next
    INDEX
    Explanations

    expressions of personal emotions and experiences

    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
    AMILY
    -0.06
     actually
    -0.06
    plus
    -0.06
     '*
    -0.06
     count
    -0.06
     nors
    -0.06
     `
    -0.06
     looks
    -0.06
     apparently
    -0.05
    -A
    -0.05
    POSITIVE LOGITS
    æĺ¯æĪij
    0.08
    uncate
    0.07
     myself
    0.07
    -placeholder
    0.07
     my
    0.07
    ç§ģãģ¯
    0.07
    atego
    0.07
    acam
    0.07
    dealloc
    0.06
    .scalablytyped
    0.06
    Activations Density 0.016%

    No Known Activations