© 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. 84144
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting actions or instructions

    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
    ONGL
    -0.07
    amburger
    -0.07
    PELL
    -0.07
    mÃŃt
    -0.06
    ĽĦ
    -0.06
    urer
    -0.06
    pects
    -0.06
    OVÃģ
    -0.06
    è¿Ļä¸Ģ
    -0.06
    ows
    -0.06
    POSITIVE LOGITS
     simply
    0.10
     yourself
    0.08
    Simply
    0.08
     simplement
    0.08
     Simply
    0.07
     directly
    0.07
     recourse
    0.07
    ame
    0.07
    oris
    0.07
     simples
    0.07
    Activations Density 0.020%

    No Known Activations