© 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. 127974
    Prev
    Next
    INDEX
    Explanations

    terms associated with testing or evaluation processes

    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
    302
    -0.07
    inkel
    -0.07
    Ìģ
    -0.06
     Kis
    -0.06
     BBC
    -0.06
    rouch
    -0.06
     Wich
    -0.06
    -0.06
    &T
    -0.06
     ent
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.09
     Kür
    0.08
    uce
    0.08
    eniable
    0.08
    biên
    0.08
    /renderer
    0.07
    addField
    0.07
    	TokenName
    0.07
    lw
    0.07
    DDS
    0.07
    Activations Density 0.000%

    No Known Activations