© 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. 56894
    Prev
    Next
    INDEX
    Explanations

    genetic mutations and inheritance patterns

    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
    ìłĪ
    -0.07
    é¾Ħ
    -0.07
    hsi
    -0.07
    orris
    -0.07
    emey
    -0.07
    zin
    -0.06
    xbb
    -0.06
    hardt
    -0.06
    orrar
    -0.06
    hub
    -0.06
    POSITIVE LOGITS
     recess
    0.07
     inheritance
    0.07
     Mend
    0.07
     trait
    0.06
     Hol
    0.06
    _race
    0.06
    Hol
    0.06
     Disease
    0.06
     Individuals
    0.06
     intro
    0.06
    Activations Density 0.008%

    No Known Activations