© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87714
    Prev
    Next
    INDEX
    Explanations

    punctuations and formatting related to dates and lists

    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
     Mick
    -0.06
    urn
    -0.06
    ews
    -0.06
    виж
    -0.06
     inv
    -0.06
     æĪ
    -0.06
    Earth
    -0.06
     MethodInfo
    -0.06
     Mandatory
    -0.05
    -tree
    -0.05
    POSITIVE LOGITS
    _inches
    0.07
    ÅĤug
    0.07
    ipi
    0.07
     Ø´ÙĩرÛĮ
    0.07
    BN
    0.06
     виÑıв
    0.06
    anol
    0.06
    lue
    0.06
    reib
    0.06
    AdapterFactory
    0.06
    Activations Density 0.000%

    No Known Activations