© 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. 119005
    Prev
    Next
    INDEX
    Explanations

    occurrences of plural forms or references to multiple items

    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
    iu
    -0.07
    ersed
    -0.07
    ystate
    -0.07
    ebi
    -0.07
    uell
    -0.07
    683
    -0.07
    redient
    -0.07
    enheim
    -0.06
    cox
    -0.06
    -sdk
    -0.06
    POSITIVE LOGITS
    bler
    0.06
    enia
    0.06
    InRange
    0.06
    اØŃ
    0.06
    ضÙĦ
    0.06
    QUIRE
    0.05
    akh
    0.05
    ROTO
    0.05
    OwnerId
    0.05
    è¾¹
    0.05
    Activations Density 0.001%

    No Known Activations