© 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. 87148
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and relationships between variables

    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
    uzey
    -0.08
    ÙĦÛĮÙĦ
    -0.07
    dateFormat
    -0.07
     targetType
    -0.07
    archive
    -0.07
    arin
    -0.07
     McB
    -0.07
    aneously
    -0.07
    бÑĸ
    -0.06
    .tools
    -0.06
    POSITIVE LOGITS
    cha
    0.07
    erea
    0.06
     replic
    0.06
    inox
    0.06
     Goldman
    0.06
    orges
    0.06
    valueOf
    0.06
     Hen
    0.05
    .getOwnProperty
    0.05
     WPARAM
    0.05
    Activations Density 0.024%

    No Known Activations