© 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. 105568
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest guidance or recommendations

    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
    eras
    -0.07
    589
    -0.07
    aways
    -0.06
    acak
    -0.06
    205
    -0.06
    555
    -0.06
    095
    -0.06
    usu
    -0.06
    995
    -0.06
    ey
    -0.06
    POSITIVE LOGITS
     details
    0.11
     information
    0.10
     info
    0.09
     more
    0.09
     informatie
    0.08
     further
    0.08
    istol
    0.08
     discussion
    0.07
     información
    0.07
    详æĥħ
    0.07
    Activations Density 0.017%

    No Known Activations