© 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. 124915
    Prev
    Next
    INDEX
    Explanations

    key information related to public health and medical research

    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
     dna
    -0.07
    meni
    -0.07
    çĦ¡ãģĹ
    -0.07
    (åľŁ
    -0.07
    ALCHEMY
    -0.06
    ardon
    -0.06
    सर
    -0.06
    ÅĦ
    -0.06
    emo
    -0.06
    embr
    -0.06
    POSITIVE LOGITS
    iox
    0.07
    amas
    0.07
    ije
    0.06
    .win
    0.06
    opens
    0.06
    æľĹ
    0.06
     Mane
    0.06
     hab
    0.06
    eres
    0.06
    .backend
    0.05
    Activations Density 0.000%

    No Known Activations