© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84724
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe quality or characteristics, particularly in a positive or notable manner

    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
    iest
    -0.08
    ATEST
    -0.07
    usercontent
    -0.07
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    -0.07
    ÙĦÛĮÙħ
    -0.07
    ixo
    -0.07
     addCriterion
    -0.06
    ingly
    -0.06
    ADOR
    -0.06
    orem
    -0.06
    POSITIVE LOGITS
    ISTA
    0.06
    ardown
    0.06
    edy
    0.06
    ooks
    0.06
    uning
    0.06
     invented
    0.05
    DED
    0.05
    UpDown
    0.05
    thren
    0.05
    иÑĩ
    0.05
    Activations Density 0.226%

    No Known Activations