© 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. 15-LLAMASCOPE-RES-131K
    11. 1129
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "spin" and its variations

    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
    een
    -0.08
    anson
    -0.07
    ikan
    -0.07
    inine
    -0.07
    oop
    -0.07
    lems
    -0.07
    ej
    -0.07
    aurus
    -0.07
    osy
    -0.07
    ablish
    -0.07
    POSITIVE LOGITS
    ning
    0.08
    -spin
    0.07
    ola
    0.07
    emann
    0.07
    ners
    0.07
    heiro
    0.07
    ãĥ«ãĥķ
    0.07
    angler
    0.07
    ÑĮко
    0.07
    igel
    0.07
    Activations Density 0.010%

    No Known Activations