© 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. 106426
    Prev
    Next
    INDEX
    Explanations

    phrases related to eligibility and selection criteria

    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
    Å©i
    -0.07
    werp
    -0.07
    erdings
    -0.07
    ãĥ³ãĥĶ
    -0.06
    ercial
    -0.06
    idlo
    -0.06
    yscale
    -0.06
     Yao
    -0.06
    anik
    -0.06
    urai
    -0.06
    POSITIVE LOGITS
     included
    0.06
    chas
    0.06
    zens
    0.06
    ji
    0.06
    åĩī
    0.06
     æ¹
    0.06
    undy
    0.06
    .Aggressive
    0.06
     bell
    0.06
    PLICATION
    0.06
    Activations Density 0.037%

    No Known Activations