© 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. 71016
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legal processes and 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
    sten
    -0.06
    aped
    -0.06
    ekl
    -0.06
    abant
    -0.06
    SC
    -0.06
     profile
    -0.06
     safe
    -0.06
     profiles
    -0.06
    anki
    -0.06
    val
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĤº
    0.08
    FormatException
    0.08
    -пÑĢав
    0.08
    _Form
    0.07
     Malone
    0.07
    _Ent
    0.07
     FORMAT
    0.07
     Format
    0.07
    ÑĢÑĸй
    0.07
     format
    0.07
    Activations Density 0.005%

    No Known Activations