© 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. 83092
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of items or situations

    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
    anza
    -0.08
    encer
    -0.07
    arming
    -0.06
    .configure
    -0.06
     early
    -0.06
     пÑĢоÑĤив
    -0.06
    268
    -0.06
    279
    -0.06
     crowd
    -0.06
    ieg
    -0.06
    POSITIVE LOGITS
     alive
    0.13
    alive
    0.10
    _alive
    0.10
    Alive
    0.09
     Alive
    0.09
    à¹Ħว
    0.09
     tabs
    0.08
    assi
    0.07
     away
    0.07
     Tabs
    0.07
    Activations Density 0.068%

    No Known Activations