© 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 EvalsExportsinterp-engineNEWAPI 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. 116802
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "arrow" 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
    rics
    -0.08
    uly
    -0.07
    TING
    -0.07
    usz
    -0.07
    üph
    -0.07
    862
    -0.07
    éı¡
    -0.07
    -session
    -0.07
     Incre
    -0.07
    istory
    -0.07
    POSITIVE LOGITS
    -shaped
    0.09
    -eyed
    0.07
    ight
    0.07
    head
    0.07
    -point
    0.07
    red
    0.07
     naked
    0.07
    ed
    0.07
     pointing
    0.07
    heads
    0.07
    Activations Density 0.006%

    No Known Activations