© 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. 4018
    Prev
    Next
    INDEX
    Explanations

    code structure and programming language elements

    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
    ÏĦαι
    -0.07
    .MixedReality
    -0.07
    isté
    -0.07
    ibs
    -0.06
     [['
    -0.06
     [["
    -0.06
    RAND
    -0.06
    adlo
    -0.06
    cesso
    -0.06
    tout
    -0.06
    POSITIVE LOGITS
     None
    0.17
    None
    0.15
    	None
    0.10
    (None
    0.10
    _none
    0.10
     \↵
    0.09
     getattr
    0.09
     False
    0.09
    _None
    0.09
     str
    0.09
    Activations Density 0.027%

    No Known Activations