© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16535
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the."

    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
    Narr
    -0.07
    æ°¸ä¹ħ
    -0.07
    áp
    -0.07
    .lex
    -0.07
    stroy
    -0.06
     sprav
    -0.06
     Kirby
    -0.06
     हव
    -0.06
    Æ¡
    -0.06
     ode
    -0.06
    POSITIVE LOGITS
     meaning
    0.09
     relation
    0.09
     concept
    0.08
     relationship
    0.08
     Relationship
    0.08
     role
    0.08
     nature
    0.07
    relation
    0.07
    meaning
    0.07
     Relation
    0.07
    Activations Density 0.037%

    No Known Activations