© 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. 94774
    Prev
    Next
    INDEX
    Explanations

    information about free services and membership programs

    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
    725
    -0.06
    odyn
    -0.06
     Anc
    -0.05
    ाफ
    -0.05
     Stam
    -0.05
     res
    -0.05
    097
    -0.05
    vable
    -0.05
    ATOM
    -0.05
    882
    -0.05
    POSITIVE LOGITS
     free
    0.28
     gratis
    0.27
    åħįè´¹
    0.27
     FREE
    0.27
    free
    0.25
    FREE
    0.24
    çĦ¡æĸĻ
    0.24
     Free
    0.21
    -free
    0.21
     kostenlos
    0.21
    Activations Density 0.164%

    No Known Activations