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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27645
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "shape" and its derivatives, indicating a focus on the concept of formation or influence

    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
    ease
    -0.07
    ea
    -0.07
    ãĥĻãĥ«
    -0.07
    tg
    -0.06
    isa
    -0.06
    iser
    -0.06
    land
    -0.06
    atis
    -0.06
    borg
    -0.06
    erce
    -0.06
    POSITIVE LOGITS
    shape
    0.11
     shape
    0.11
     Shape
    0.10
    (shape
    0.10
     shaped
    0.10
     shapes
    0.09
    .shape
    0.08
    -shaped
    0.08
    less
    0.08
    lessly
    0.08
    Activations Density 0.019%

    No Known Activations