© 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. 55896
    Prev
    Next
    INDEX
    Explanations

    instances of formality and procedural language in discussions

    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
    pons
    -0.07
    opus
    -0.07
    Ø·Ùĩ
    -0.06
    Ñģли
    -0.06
    INGLE
    -0.06
    ongan
    -0.06
    ÃĵN
    -0.06
    LOPT
    -0.06
    oot
    -0.06
    Caller
    -0.06
    POSITIVE LOGITS
     appearances
    0.10
     facade
    0.10
    æķ·
    0.08
     appearance
    0.08
     nominal
    0.08
     lip
    0.08
     Appearance
    0.07
     appe
    0.07
     superficial
    0.07
     merely
    0.07
    Activations Density 0.085%

    No Known Activations