© 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. 40183
    Prev
    Next
    INDEX
    Explanations

    names of countries and regions mentioned in relation to specific contexts or issues

    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
    odont
    -0.07
    kowski
    -0.07
    lessly
    -0.07
    loff
    -0.07
    ongsTo
    -0.07
     Hlav
    -0.07
    mite
    -0.07
    roi
    -0.06
    ingly
    -0.06
     Tits
    -0.06
    POSITIVE LOGITS
    -wide
    0.07
    /world
    0.07
    -American
    0.07
    -Israel
    0.07
    å¾
    0.06
    weit
    0.06
    «ĺ
    0.06
    /Linux
    0.06
     FieldType
    0.06
    -Compatible
    0.06
    Activations Density 0.081%

    No Known Activations