© 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. 17-LLAMASCOPE-RES-131K
    6. 77498
    Prev
    Next
    INDEX
    Explanations

    similes or comparisons using the word "like."

    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
    yme
    -0.07
    exus
    -0.07
    IGHL
    -0.06
    ihat
    -0.06
    anvas
    -0.06
    ancode
    -0.06
     UnityEditor
    -0.06
    archy
    -0.06
     célib
    -0.06
    ken
    -0.06
    POSITIVE LOGITS
     clock
    0.09
    ieri
    0.07
     CLOCK
    0.06
     Lair
    0.06
    aju
    0.06
     McMahon
    0.06
    -clock
    0.06
     Ske
    0.06
    cle
    0.06
    ioni
    0.06
    Activations Density 0.015%

    No Known Activations