© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78669
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "timing" and making plans

    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
    uty
    -0.06
    ools
    -0.06
    ÙİØ£
    -0.06
     earlier
    -0.06
     eventual
    -0.06
    uth
    -0.05
    åύ
    -0.05
    ibox
    -0.05
    uch
    -0.05
    igel
    -0.05
    POSITIVE LOGITS
    occo
    0.08
    akin
    0.08
    Ø¡
    0.07
     someone
    0.07
    ewise
    0.07
     паÑģ
    0.07
    ÑĥÑģка
    0.07
    amarin
    0.07
     yourselves
    0.07
    someone
    0.07
    Activations Density 0.005%

    No Known Activations