© 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. 40735
    Prev
    Next
    INDEX
    Explanations

    Java language identifiers or references

    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
    ickle
    -0.08
    nee
    -0.06
    icky
    -0.06
    ÑĢен
    -0.06
    sock
    -0.06
    leton
    -0.05
    ont
    -0.05
    hatt
    -0.05
    omp
    -0.05
    ole
    -0.05
    POSITIVE LOGITS
    ERVED
    0.07
    merce
    0.07
    uments
    0.07
    że
    0.07
    ething
    0.07
    alÄ±ÅŁ
    0.07
     Paladin
    0.07
    ioni
    0.07
     CONSEQUENTIAL
    0.07
    .lang
    0.07
    Activations Density 0.003%

    No Known Activations