© 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. 16010
    Prev
    Next
    INDEX
    Explanations

    references to academic journal articles and their citation formats

    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
    abra
    -0.07
    uries
    -0.07
    riday
    -0.07
    ÑĥÑĪка
    -0.07
    à¹Īà¸ĩà¸Ĥ
    -0.06
    ihan
    -0.06
    orget
    -0.06
    ikel
    -0.06
    ryn
    -0.06
    ocus
    -0.06
    POSITIVE LOGITS
     Sesso
    0.07
     Champ
    0.06
     Cha
    0.06
    Cha
    0.06
    éĥ¡
    0.06
    edn
    0.06
     Coord
    0.06
     DCHECK
    0.06
    #echo
    0.06
    Unity
    0.06
    Activations Density 0.010%

    No Known Activations