© 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. 88965
    Prev
    Next
    INDEX
    Explanations

    components related to academic authorship and publication data

    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
    ufen
    -0.07
    UIL
    -0.07
    meno
    -0.07
    ikal
    -0.07
     noh
    -0.07
    raki
    -0.07
     huz
    -0.06
    ÐĶÐIJ
    -0.06
    undler
    -0.06
    819
    -0.06
    POSITIVE LOGITS
    asca
    0.07
    innacle
    0.06
     {.
    0.06
     ÐłÐ¾ÑģÑģийÑģкой
    0.05
    CES
    0.05
    ritch
    0.05
    su
    0.05
     Manning
    0.05
    (CharSequence
    0.05
    CAPE
    0.05
    Activations Density 0.001%

    No Known Activations