© 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. 40665
    Prev
    Next
    INDEX
    Explanations

    references to significant global events or economic implications

    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
    avad
    -0.08
    á»Ĩ
    -0.08
    uchos
    -0.08
    ptal
    -0.07
     dziew
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    á»ĩu
    -0.07
    chaft
    -0.07
    çĭ
    -0.07
    DITION
    -0.07
    POSITIVE LOGITS
    ,
    0.07
     Dit
    0.07
    .
    0.07
     pronto
    0.07
     thing
    0.06
     (
    0.06
     ones
    0.06
     Nay
    0.06
    asing
    0.06
    0.06
    Activations Density 0.000%

    No Known Activations