© 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. 84049
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the conjunction "and"

    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
     _______,
    -0.08
    èĻ½çĦ¶
    -0.07
    ãĢģãģĿãĤĮ
    -0.07
    ittest
    -0.07
    .persist
    -0.07
    unner
    -0.06
     бÑĥк
    -0.06
    ERCHANT
    -0.06
     dh
    -0.06
    _Destroy
    -0.06
    POSITIVE LOGITS
    agate
    0.07
    enty
    0.06
    OfType
    0.06
     ìŀĪìĬµëĭĪëĭ¤
    0.06
     indeed
    0.06
    جع
    0.06
    abler
    0.06
    "./
    0.06
    vida
    0.06
    anzi
    0.06
    Activations Density 0.046%

    No Known Activations