© 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. 87851
    Prev
    Next
    INDEX
    Explanations

    phrases that express denial or negate statements

    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
     Kund
    -0.07
     Reminder
    -0.06
    fact
    -0.06
     caul
    -0.06
    oss
    -0.06
    eÅŁ
    -0.06
    NavigationView
    -0.06
    acia
    -0.06
    bread
    -0.06
    ause
    -0.06
    POSITIVE LOGITS
    ihan
    0.07
    ụ
    0.07
    irth
    0.07
     discern
    0.06
    jid
    0.06
    Ñī
    0.06
     fing
    0.06
    riangle
    0.06
     contest
    0.06
    orias
    0.06
    Activations Density 0.008%

    No Known Activations