© 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. 5-LLAMASCOPE-RES-131K
    11. 125738
    Prev
    Next
    INDEX
    Explanations

    terms related to hormonal treatments and therapies

    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
    eous
    -0.07
    ners
    -0.07
    lernen
    -0.07
    bourg
    -0.07
    reen
    -0.07
    ei
    -0.07
    tring
    -0.07
    _hooks
    -0.07
    -ÑĤаки
    -0.07
    áºŃp
    -0.07
    POSITIVE LOGITS
    igon
    0.07
    (IR
    0.06
    utton
    0.06
     Laud
    0.06
    edges
    0.06
     ne
    0.06
     pap
    0.05
    IG
    0.05
    imoto
    0.05
    ousedown
    0.05
    Activations Density 0.001%

    No Known Activations