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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96156
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and file versioning information

    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
    nech
    -0.07
     originals
    -0.07
    -urlencoded
    -0.06
    bah
    -0.06
    pet
    -0.06
    DAQ
    -0.06
     Princip
    -0.06
    Jar
    -0.06
    quine
    -0.06
    /Runtime
    -0.06
    POSITIVE LOGITS
    adero
    0.07
    estre
    0.07
    ãĤ¤ãĥ³ãĥĪ
    0.07
    EEK
    0.07
    .Enc
    0.07
    .metro
    0.06
    elle
    0.06
    âĹİ
    0.06
     Lager
    0.06
    лаж
    0.06
    Activations Density 0.005%

    No Known Activations