© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126585
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in some cases."

    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
    alytics
    -0.07
    ongyang
    -0.07
    ong
    -0.07
    ral
    -0.07
    ventus
    -0.06
    kul
    -0.06
    ksi
    -0.06
    tle
    -0.06
    raphics
    -0.06
    (çģ«
    -0.06
    POSITIVE LOGITS
     Roller
    0.06
     Cabr
    0.06
    ipp
    0.06
     roller
    0.06
    ROLL
    0.06
    æĮ¯
    0.06
    KeyListener
    0.06
     Jacqu
    0.06
    çĶļ
    0.06
    .Schema
    0.06
    Activations Density 0.006%

    No Known Activations