© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95147
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contact information or accessibility

    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
    endforeach
    -0.07
    enheim
    -0.06
    ilip
    -0.06
    ippo
    -0.06
     races
    -0.06
    ica
    -0.06
    icher
    -0.06
     sle
    -0.06
    resse
    -0.06
    ique
    -0.05
    POSITIVE LOGITS
    apg
    0.08
    istrovstvÃŃ
    0.07
    ĶåĽŀ
    0.07
    uhn
    0.07
     nÄĥ
    0.07
    ept
    0.07
    ldr
    0.07
    udiant
    0.06
    çĦ¼
    0.06
    ctxt
    0.06
    Activations Density 0.003%

    No Known Activations