© 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. 85947
    Prev
    Next
    INDEX
    Explanations

    references to being part of a group or highlighting collective experiences

    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
    iling
    -0.07
    lix
    -0.07
    chen
    -0.07
    itable
    -0.07
    evenodd
    -0.06
    ILING
    -0.06
    ãĥĥãĤ¯ãĤ¹
    -0.06
    illin
    -0.06
    ENS
    -0.06
    akin
    -0.06
    POSITIVE LOGITS
     things
    0.08
    veis
    0.07
     пÑĢоÑĩ
    0.07
    (thing
    0.07
    things
    0.06
    serial
    0.06
     cosas
    0.06
     Else
    0.06
     thing
    0.06
    Thing
    0.06
    Activations Density 0.004%

    No Known Activations