© 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. 77789
    Prev
    Next
    INDEX
    Explanations

    terms related to various fields of knowledge and their applications

    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
    å·ŀå¸Ĥ
    -0.10
    å±±å¸Ĥ
    -0.10
    ISCO
    -0.09
     vur
    -0.08
    antas
    -0.08
    داد
    -0.08
    auce
    -0.07
    agas
    -0.07
    _ABI
    -0.07
    iyas
    -0.07
    POSITIVE LOGITS
    ,
    0.07
    0.06
     ones
    0.06
    áŀ¶
    0.06
    :
    0.06
    iation
    0.06
    ;
    0.06
     Jeh
    0.06
     (
    0.05
     Eld
    0.05
    Activations Density 0.095%

    No Known Activations