© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61993
    Prev
    Next
    INDEX
    Explanations

    terms related to competitive events and contests

    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
     nues
    -0.07
    ango
    -0.06
    moduleName
    -0.06
     Nha
    -0.06
    enant
    -0.06
     è¡
    -0.06
     pans
    -0.06
    μία
    -0.06
    ällt
    -0.06
    odie
    -0.06
    POSITIVE LOGITS
    igan
    0.07
    ropa
    0.07
    DP
    0.06
    czy
    0.06
    weg
    0.06
     Ùħص
    0.06
    .dc
    0.06
    å´
    0.06
    uchos
    0.06
    lot
    0.06
    Activations Density 0.002%

    No Known Activations