© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4263
    Prev
    Next
    INDEX
    Explanations

    information related to the announcement of a childbirth

    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
    TOTYPE
    -0.07
    marshall
    -0.07
    بÙĪØ¯
    -0.07
    panion
    -0.06
    grund
    -0.06
    _capabilities
    -0.06
    usty
    -0.06
     Abort
    -0.06
    ायद
    -0.06
    ľĺ
    -0.06
    POSITIVE LOGITS
    amb
    0.07
     birth
    0.07
    ãĤº
    0.06
    ewe
    0.06
     names
    0.06
    hlen
    0.06
    nels
    0.06
    lij
    0.06
    adr
    0.06
     suite
    0.06
    Activations Density 0.010%

    No Known Activations