© 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 EvalsExportsinterp-engineNEWAPI 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. 69599
    Prev
    Next
    INDEX
    Explanations

    quantitative or numerical data references

    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
     redund
    -0.06
    .apps
    -0.06
     LEN
    -0.06
     unt
    -0.06
     Shack
    -0.06
     PED
    -0.05
     Len
    -0.05
     ae
    -0.05
     Outlet
    -0.05
    éĸĵãģ«
    -0.05
    POSITIVE LOGITS
    RowAt
    0.07
    SGlobal
    0.07
    .decor
    0.07
    olle
    0.07
    venir
    0.07
    æ´¾
    0.07
    tega
    0.07
     Farrell
    0.07
    onal
    0.07
    SCALL
    0.07
    Activations Density 0.001%

    No Known Activations