© 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. 22-LLAMASCOPE-RES-131K
    11. 3944
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "for that matter."

    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
    åĨ
    -0.07
     —↵↵
    -0.07
    .gdx
    -0.07
    anton
    -0.06
     nackte
    -0.06
    scoped
    -0.06
    éī
    -0.06
    ç²
    -0.06
    rts
    -0.06
    URI
    -0.06
    POSITIVE LOGITS
     matter
    0.36
    matter
    0.31
     Matter
    0.28
     matters
    0.27
     Matters
    0.21
     mattered
    0.20
    atter
    0.15
    ATTER
    0.14
     mater
    0.14
     MAT
    0.13
    Activations Density 0.003%

    No Known Activations