© 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. 29781
    Prev
    Next
    INDEX
    Explanations

    occurrences of phrases indicating location or context

    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
     another
    -0.08
    rin
    -0.06
     otra
    -0.06
    another
    -0.06
    dsa
    -0.06
    eper
    -0.06
     some
    -0.06
     Lastly
    -0.06
     other
    -0.06
     closure
    -0.06
    POSITIVE LOGITS
    agini
    0.08
     unlike
    0.07
     Unlike
    0.07
    ãģ¾ãģļ
    0.07
    Unlike
    0.07
    arsi
    0.07
    apore
    0.07
    ç¿Ķ
    0.06
    APPER
    0.06
    swer
    0.06
    Activations Density 0.034%

    No Known Activations