© 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. 56322
    Prev
    Next
    INDEX
    Explanations

    expressions related to freshness and newness

    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
    ANS
    -0.06
    ChangeEvent
    -0.06
    strict
    -0.06
    acos
    -0.06
    ood
    -0.06
    asu
    -0.06
    gest
    -0.06
     Wol
    -0.06
    371
    -0.06
    DESC
    -0.06
    POSITIVE LOGITS
     fresh
    0.12
    fresh
    0.10
    ening
    0.10
    ened
    0.10
     fres
    0.09
    /new
    0.09
    é²ľ
    0.09
     Ñģвеж
    0.09
    Fresh
    0.09
    é®®
    0.09
    Activations Density 0.011%

    No Known Activations