© 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. 76739
    Prev
    Next
    INDEX
    Explanations

    references to legislation and regulatory actions in various contexts

    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
    çĬ¶æ³ģ
    -0.07
     RTBU
    -0.07
    _BOTH
    -0.07
    tingham
    -0.07
    eut
    -0.06
     strSql
    -0.06
    _APPS
    -0.06
    ãĥ«ãĤ¯
    -0.06
    ç²¾åĵģ
    -0.06
    CTIONS
    -0.06
    POSITIVE LOGITS
     certain
    0.07
    vers
    0.07
     Vers
    0.06
     ¬
    0.06
     Certain
    0.06
    kre
    0.06
    iel
    0.06
    "http
    0.06
     versus
    0.06
    ire
    0.06
    Activations Density 0.050%

    No Known Activations