© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56161
    Prev
    Next
    INDEX
    Explanations

    instructions or guidance on how to complete tasks

    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
    quo
    -0.07
     fitte
    -0.07
    å®ļçļĦ
    -0.07
    antino
    -0.07
    ÙĪا
    -0.07
    åĥ
    -0.07
    ãĤıãģĽ
    -0.06
    izr
    -0.06
    oproject
    -0.06
    ói
    -0.06
    POSITIVE LOGITS
     directions
    0.10
     how
    0.10
     direction
    0.09
     instructions
    0.09
     correct
    0.08
    how
    0.08
    å¦Ĥä½ķ
    0.07
     Directions
    0.07
    direction
    0.07
     optimum
    0.07
    Activations Density 0.035%

    No Known Activations