© 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. 61241
    Prev
    Next
    INDEX
    Explanations

    statements or claims regarding historical events and figures

    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
    âĻª
    -0.07
    aran
    -0.06
    linger
    -0.06
     Lif
    -0.06
     liv
    -0.06
    brush
    -0.06
     corner
    -0.06
    lif
    -0.06
     mount
    -0.06
     Obr
    -0.06
    POSITIVE LOGITS
    dden
    0.07
    iscrim
    0.07
    μιÏĥ
    0.07
    bjerg
    0.07
    uen
    0.07
    ÐĶÐļ
    0.07
    yonel
    0.06
    uzzle
    0.06
     Fully
    0.06
    iros
    0.06
    Activations Density 0.011%

    No Known Activations