© 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. 5-LLAMASCOPE-RES-131K
    11. 125859
    Prev
    Next
    INDEX
    Explanations

    terms related to progress or advancements

    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
    rets
    -0.07
    esium
    -0.07
    ume
    -0.06
    atoi
    -0.06
    cimal
    -0.06
    imeType
    -0.06
    agna
    -0.06
    981
    -0.06
    esar
    -0.06
    á»įt
    -0.06
    POSITIVE LOGITS
     _{}
    0.06
    backs
    0.06
    anks
    0.06
    ATUS
    0.06
    luž
    0.06
    ntax
    0.06
    ÃľRK
    0.06
    disable
    0.06
    edn
    0.06
     into
    0.06
    Activations Density 0.001%

    No Known Activations