© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4035
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming constructs and macro functionalities

    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
     aktu
    -0.07
    immers
    -0.07
     Buccane
    -0.06
    iyon
    -0.06
     patron
    -0.06
    864
    -0.06
    lags
    -0.06
    pios
    -0.06
    é¢Ħè§Ī
    -0.06
    æ¦
    -0.06
    POSITIVE LOGITS
     reserved
    0.10
    reserved
    0.08
     reserve
    0.08
     Reserved
    0.08
     Reserve
    0.08
    Reserved
    0.07
     reservation
    0.07
     RESERVED
    0.07
     commonly
    0.07
    reserve
    0.07
    Activations Density 0.025%

    No Known Activations