© 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. 5-LLAMASCOPE-RES-131K
    11. 126096
    Prev
    Next
    INDEX
    Explanations

    exceptions related to null and argument errors in programming

    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
    evin
    -0.07
    eo
    -0.07
    Phones
    -0.07
     TÆ°
    -0.07
    ADDE
    -0.07
    ematic
    -0.06
    ein
    -0.06
    COME
    -0.06
    ems
    -0.06
    Writes
    -0.06
    POSITIVE LOGITS
    ss
    0.06
    yses
    0.06
     truly
    0.06
    .resp
    0.06
     Resp
    0.06
     Building
    0.06
    ãĥĥãĥĦ
    0.06
    atz
    0.06
     building
    0.06
     Bernardino
    0.06
    Activations Density 0.000%

    No Known Activations