© 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. 78140
    Prev
    Next
    INDEX
    Explanations

    measurements in centimeters

    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
    ilst
    -0.08
    iesel
    -0.06
     Lar
    -0.06
     segreg
    -0.06
    aille
    -0.06
    ảo
    -0.06
    ollo
    -0.06
    oteca
    -0.06
    unj
    -0.06
    antu
    -0.06
    POSITIVE LOGITS
     Neutral
    0.08
    /renderer
    0.08
     neutral
    0.08
     اÙĦÙĨظاÙħ
    0.07
    asi
    0.07
    neutral
    0.06
     Consent
    0.06
    Amazon
    0.06
    ichten
    0.06
    felt
    0.06
    Activations Density 0.000%

    No Known Activations