© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    functions or method calls involving data manipulation or processing

    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
    hay
    -0.07
    (CharSequence
    -0.07
    WhiteSpace
    -0.07
    orda
    -0.06
    à¸İ
    -0.06
    åĢī
    -0.06
    Ģ
    -0.06
    isi
    -0.06
    aeda
    -0.06
    .EventType
    -0.06
    POSITIVE LOGITS
     true
    0.08
    true
    0.07
    ÅĻen
    0.06
    ahl
    0.06
     True
    0.06
    ollections
    0.06
    सल
    0.06
    agher
    0.06
    True
    0.06
    geh
    0.06
    Activations Density 0.047%

    No Known Activations