© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124928
    Prev
    Next
    INDEX
    Explanations

    phrases indicating user engagement with a website or content

    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
    odore
    -0.06
    umbo
    -0.06
    Ñľ
    -0.06
    reten
    -0.06
     pup
    -0.06
    ota
    -0.05
    ote
    -0.05
     varied
    -0.05
    輯
    -0.05
     branch
    -0.05
    POSITIVE LOGITS
    uluk
    0.07
    urum
    0.07
    avir
    0.07
    uen
    0.07
    çĥ¦
    0.07
    pez
    0.07
    ogany
    0.07
    aroo
    0.07
    IFA
    0.07
    gorm
    0.07
    Activations Density 0.002%

    No Known Activations