© 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. 15-LLAMASCOPE-RES-131K
    11. 909
    Prev
    Next
    INDEX
    Explanations

    references to academic or professional institutions and their locations

    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
    ifest
    -0.07
    amd
    -0.07
    ellas
    -0.06
    amac
    -0.06
    erd
    -0.05
    ican
    -0.05
     exclusion
    -0.05
     speculative
    -0.05
    ather
    -0.05
    amet
    -0.05
    POSITIVE LOGITS
    ÑĢиг
    0.07
     gÃł
    0.07
     Tüm
    0.07
    ÙĨب
    0.07
    .AutoScaleMode
    0.06
    aÅĻ
    0.06
     KeyCode
    0.06
    ìĿ´ëĵľ
    0.06
    ØŃÙħ
    0.06
    ľĺ
    0.06
    Activations Density 0.004%

    No Known Activations