© 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. 15-LLAMASCOPE-RES-131K
    11. 27346
    Prev
    Next
    INDEX
    Explanations

    references to data management and processing 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
     SHARES
    -0.07
    (#)
    -0.07
    eya
    -0.07
    greg
    -0.07
    ÙĪÛĮÛĮ
    -0.07
    ECTOR
    -0.07
    ennes
    -0.07
    VERTISEMENT
    -0.07
    ftype
    -0.06
    ÑģÑĤÑĥп
    -0.06
    POSITIVE LOGITS
    ilon
    0.07
     those
    0.07
    ãĥ³ãĥĨ
    0.06
    arov
    0.06
    jem
    0.06
    éĤ£äºĽ
    0.06
    aura
    0.06
    orno
    0.06
     owners
    0.05
     batch
    0.05
    Activations Density 0.006%

    No Known Activations