© 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. 128921
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and concepts related to partitions and homomorphisms

    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
     plasma
    -0.08
     Farms
    -0.07
     Plasma
    -0.07
     pare
    -0.06
     Lik
    -0.06
    antz
    -0.06
    loven
    -0.06
    odata
    -0.06
    deme
    -0.06
    parm
    -0.06
    POSITIVE LOGITS
    alink
    0.08
     Brewery
    0.06
    ené
    0.06
     oper
    0.06
    FRING
    0.06
    çݯ
    0.06
    characters
    0.06
     ÑģпÑĢав
    0.06
     inj
    0.06
     Mitar
    0.06
    Activations Density 0.135%

    No Known Activations