© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82688
    Prev
    Next
    INDEX
    Explanations

    references to passports and related travel documentation requirements

    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
    unnable
    -0.07
    edata
    -0.06
    ebi
    -0.06
    .volley
    -0.06
    iero
    -0.06
    .prot
    -0.06
    ायà¤ķ
    -0.06
    inger
    -0.06
    Sender
    -0.06
    /tutorial
    -0.06
    POSITIVE LOGITS
     record
    0.09
     Record
    0.09
     recording
    0.09
     stamp
    0.08
     witnessing
    0.08
    Record
    0.08
    signature
    0.07
     recorded
    0.07
    record
    0.07
    stamp
    0.07
    Activations Density 0.026%

    No Known Activations