© 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. 128011
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and ownership details

    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
    444
    -0.06
    ISING
    -0.06
    ÑĢÑĮ
    -0.06
    getPost
    -0.06
    UMB
    -0.06
     dint
    -0.06
    zc
    -0.06
     Alman
    -0.05
    opo
    -0.05
     Hatch
    -0.05
    POSITIVE LOGITS
    erator
    0.08
    cai
    0.07
    iglia
    0.07
    .scalablytyped
    0.07
     kia
    0.07
    atee
    0.07
    ifter
    0.06
    aux
    0.06
    ÙĦاÙĨ
    0.06
    quirer
    0.06
    Activations Density 0.001%

    No Known Activations