© 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. 89994
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "-ose" or similarly sounding endings

    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
    swers
    -0.08
    ontrol
    -0.07
    shapes
    -0.06
    âĢ°
    -0.06
    ero
    -0.06
    صÙĪÙĦ
    -0.06
    lazy
    -0.06
    zas
    -0.06
    digits
    -0.06
    ZY
    -0.06
    POSITIVE LOGITS
    attle
    0.07
    ure
    0.07
    vere
    0.07
    ATTLE
    0.07
    elen
    0.07
    mana
    0.06
    bast
    0.06
    ums
    0.06
    vier
    0.06
    ULL
    0.06
    Activations Density 0.087%

    No Known Activations