© 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. 56798
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or symbols indicating structure in text

    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
    iram
    -0.08
    declspec
    -0.06
    ansa
    -0.06
    captcha
    -0.06
    rana
    -0.06
    ercul
    -0.06
    ecast
    -0.06
    aml
    -0.06
     ÐĶив
    -0.06
    atomy
    -0.06
    POSITIVE LOGITS
    sig
    0.08
     sig
    0.06
     dinh
    0.06
    lac
    0.06
    SIG
    0.06
     Supply
    0.06
    iae
    0.06
     supply
    0.06
    811
    0.05
    Dr
    0.05
    Activations Density 0.000%

    No Known Activations