© 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. 129496
    Prev
    Next
    INDEX
    Explanations

    time stamps and date 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
    rms
    -0.08
    mania
    -0.07
    lain
    -0.07
    æŀľ
    -0.07
    cept
    -0.07
    ajor
    -0.07
     جد
    -0.06
    ivals
    -0.06
    esters
    -0.06
    Äįel
    -0.06
    POSITIVE LOGITS
     Vir
    0.06
    دÙĩ
    0.06
     Fly
    0.06
     rein
    0.06
     tunes
    0.06
    ilim
    0.06
    avir
    0.06
    iona
    0.05
    berry
    0.05
     Faith
    0.05
    Activations Density 0.001%

    No Known Activations