© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71026
    Prev
    Next
    INDEX
    Explanations

    references to international agreements or policies

    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
    zel
    -0.07
    uing
    -0.07
    tk
    -0.07
    angelo
    -0.07
    èĤ
    -0.06
    issant
    -0.06
    ipsis
    -0.06
    _EOL
    -0.06
    noop
    -0.06
    oproject
    -0.06
    POSITIVE LOGITS
    ernet
    0.07
    fire
    0.06
     Ordering
    0.06
    亡
    0.06
    847
    0.06
     recip
    0.05
     Aure
    0.05
    _interaction
    0.05
    amedi
    0.05
    ran
    0.05
    Activations Density 0.004%

    No Known Activations