© 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. 84488
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intention

    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
    åĭĩ
    -0.08
    supply
    -0.07
    ARGIN
    -0.07
    _DECL
    -0.07
    Supply
    -0.07
     secara
    -0.07
    åħ¬åħ±
    -0.07
    /ay
    -0.06
     zwar
    -0.06
    wer
    -0.06
    POSITIVE LOGITS
     success
    0.12
     successful
    0.10
    success
    0.08
    æĪIJåĬŁ
    0.08
    -success
    0.08
     ÑĥÑģп
    0.08
     Success
    0.07
     understanding
    0.07
     succes
    0.07
     successfully
    0.07
    Activations Density 0.007%

    No Known Activations