© 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. 58198
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic or literary contexts

    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
     cust
    -0.07
    cust
    -0.06
    itational
    -0.06
    ocale
    -0.06
     Wak
    -0.06
     Dol
    -0.06
    .uf
    -0.06
    ìŀIJìĿ¸
    -0.06
    _SELF
    -0.06
     Jord
    -0.06
    POSITIVE LOGITS
    ottes
    0.07
    CRYPT
    0.06
    OTTOM
    0.06
    istrovstvÃŃ
    0.06
    itemap
    0.06
    YLON
    0.06
    veis
    0.06
    IGATION
    0.06
    ظاÙħ
    0.06
    /ns
    0.06
    Activations Density 0.006%

    No Known Activations