© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119621
    Prev
    Next
    INDEX
    Explanations

    critical observations and issues regarding social networks and partnerships

    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
    nt
    -0.07
    зÑĥ
    -0.06
    rey
    -0.06
    aniem
    -0.06
    lp
    -0.06
    arence
    -0.06
    arias
    -0.05
     Matthias
    -0.05
     IllegalAccessException
    -0.05
     sh
    -0.05
    POSITIVE LOGITS
     paradise
    0.08
     success
    0.07
    success
    0.07
     newfound
    0.07
     perfection
    0.07
    emu
    0.07
    (success
    0.07
    jid
    0.07
    uccess
    0.07
     haste
    0.07
    Activations Density 0.053%

    No Known Activations