© 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. 70772
    Prev
    Next
    INDEX
    Explanations

    references to community events and initiatives

    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
     ков
    -0.08
    rophe
    -0.07
    omor
    -0.06
    PLEX
    -0.06
     Tas
    -0.06
    éĶ¦
    -0.06
    antha
    -0.06
    anos
    -0.06
     interp
    -0.06
    icios
    -0.06
    POSITIVE LOGITS
     Urb
    0.08
     secret
    0.08
     Secret
    0.08
    zas
    0.07
     participants
    0.07
     urban
    0.07
    participants
    0.07
    urban
    0.07
    geist
    0.07
     urb
    0.07
    Activations Density 0.001%

    No Known Activations