© 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. 94089
    Prev
    Next
    INDEX
    Explanations

    references to specific years and legal concepts related to securities or financial regulations

    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
    ere
    -0.06
    mes
    -0.06
    KA
    -0.06
    ECTOR
    -0.06
     mes
    -0.05
    plural
    -0.05
    ôt
    -0.05
    amina
    -0.05
     Hang
    -0.05
    èµĦ
    -0.05
    POSITIVE LOGITS
     Incontri
    0.10
    .scalablytyped
    0.07
    .nih
    0.07
    DDS
    0.07
    ÙĬÙĨØ©
    0.07
    $l
    0.07
    xDD
    0.07
     Cumberland
    0.06
     NGX
    0.06
    .dtd
    0.06
    Activations Density 0.001%

    No Known Activations