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

    Neuronpedia

    Jacobian LensNEW
    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. 74999
    Prev
    Next
    INDEX
    Explanations

    terms related to breastfeeding and its effects on child microbiome development

    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
     Pregn
    -0.07
    ropoda
    -0.07
    GetMethod
    -0.07
    @student
    -0.07
    ç´
    -0.07
    æ®ĭ
    -0.07
     бÑĢа
    -0.07
    preg
    -0.07
    bra
    -0.07
    ÙĬÙĦاد
    -0.07
    POSITIVE LOGITS
     exclusive
    0.08
     Exclusive
    0.07
     iron
    0.07
    vero
    0.07
    earer
    0.07
     lifelong
    0.07
    Exclusive
    0.06
    oler
    0.06
     bonding
    0.06
    ноÑģÑĤÑĮÑİ
    0.06
    Activations Density 0.002%

    No Known Activations