© 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. 77375
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements and community recognition

    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
    asto
    -0.09
    istrovstvÃŃ
    -0.07
    atsby
    -0.07
    074
    -0.06
    FER
    -0.06
    PLY
    -0.06
    .kotlin
    -0.06
    207
    -0.06
    edo
    -0.06
     damn
    -0.06
    POSITIVE LOGITS
    夫
    0.07
    夫人
    0.07
    ï¼Īå¹³æĪIJ
    0.07
    寺
    0.06
     Haley
    0.06
    (++
    0.06
     katı
    0.06
    ourse
    0.06
     McGr
    0.06
    anc
    0.06
    Activations Density 0.001%

    No Known Activations