© 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. 106105
    Prev
    Next
    INDEX
    Explanations

    instances of the word "no" in various contexts

    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
    olib
    -0.08
    ailability
    -0.08
    affen
    -0.08
    à¹Ģà¸ģà¸Ńร
    -0.08
    gio
    -0.08
    enco
    -0.07
    ijke
    -0.07
    Ø´ÙĪ
    -0.07
    ged
    -0.07
    rez
    -0.07
    POSITIVE LOGITS
    ender
    0.06
     tender
    0.06
     Tender
    0.05
     weiter
    0.05
     further
    0.05
    enders
    0.05
    042
    0.05
     complicated
    0.05
     stopping
    0.05
    455
    0.05
    Activations Density 0.001%

    No Known Activations