© 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. 17-LLAMASCOPE-RES-131K
    6. 40282
    Prev
    Next
    INDEX
    Explanations

    text related to dates and timelines

    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
     Merge
    -0.06
    ves
    -0.06
    px
    -0.06
    ify
    -0.06
    497
    -0.05
    832
    -0.05
    ners
    -0.05
    532
    -0.05
    itters
    -0.05
     Concurrent
    -0.05
    POSITIVE LOGITS
    }č↵č↵č↵č↵
    0.07
    SSI
    0.07
    TEGER
    0.07
     Uncategorized
    0.07
    ahi
    0.07
    }č↵č↵č↵
    0.07
     Pas
    0.06
    appen
    0.06
    antes
    0.06
     célib
    0.06
    Activations Density 0.002%

    No Known Activations