© 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. 82514
    Prev
    Next
    INDEX
    Explanations

    statements and references made by spokespersons and officials

    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
    ptype
    -0.07
     Sons
    -0.07
    zier
    -0.07
     vict
    -0.06
     Ach
    -0.06
    ipo
    -0.06
     заклад
    -0.06
    è¨Ĥ
    -0.06
     Barg
    -0.06
    oney
    -0.06
    POSITIVE LOGITS
    obox
    0.08
    orz
    0.07
    arus
    0.07
    ibox
    0.07
    agli
    0.06
     âĸij
    0.06
    arto
    0.06
    anel
    0.06
    GetEnumerator
    0.06
    ocker
    0.06
    Activations Density 0.008%

    No Known Activations