© 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. 15-LLAMASCOPE-RES-131K
    11. 89344
    Prev
    Next
    INDEX
    Explanations

    references to important finishing moments or conclusions in events

    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
    éĢģæĸĻçĦ¡æĸĻ
    -0.08
    siz
    -0.07
    ritel
    -0.07
    /umd
    -0.07
    ioned
    -0.07
    -toggler
    -0.07
    htable
    -0.07
    ients
    -0.07
    пеÑĩ
    -0.07
    zung
    -0.06
    POSITIVE LOGITS
    est
    0.07
    uition
    0.06
    -c
    0.06
     Executes
    0.06
    Unsafe
    0.06
     BorderSide
    0.06
    312
    0.06
    ÙĦاÙĤ
    0.06
     few
    0.06
    evin
    0.06
    Activations Density 0.006%

    No Known Activations