Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126377
    Prev
    Next
    INDEX
    Explanations

    references to various types of payment cards and card-related transactions

    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
    asar
    -0.07
    entin
    -0.07
    aml
    -0.07
    iferay
    -0.07
    lander
    -0.07
    _GRE
    -0.07
     Werk
    -0.06
    æijĺ
    -0.06
    tml
    -0.06
    endency
    -0.06
    POSITIVE LOGITS
    enburg
    0.06
     Colonial
    0.06
    éĸ
    0.06
     pel
    0.06
    .buf
    0.06
     Sanford
    0.06
    ÏĥÏĥ
    0.05
    ánh
    0.05
    ER
    0.05
    ingleton
    0.05
    Activations Density 0.006%

    No Known Activations