© 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. 125412
    Prev
    Next
    INDEX
    Explanations

    specific sports figures and related events

    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
    ansi
    -0.06
     Hawai
    -0.06
     Option
    -0.06
    Ïģαβ
    -0.06
    çon
    -0.05
    ãĥģãĥ¥
    -0.05
    à¤Ķ
    -0.05
    ÑĥÑģÑĤ
    -0.05
    /epl
    -0.05
    åĭ¤
    -0.05
    POSITIVE LOGITS
    umba
    0.07
     numberWith
    0.07
    buat
    0.07
    ìĿµ
    0.07
    iffe
    0.07
    General
    0.07
    ount
    0.07
    ataka
    0.06
    ardware
    0.06
    InBackground
    0.06
    Activations Density 0.004%

    No Known Activations