© 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. 15-LLAMASCOPE-RES-131K
    6. 965
    Prev
    Next
    INDEX
    Explanations

    references to common vulnerabilities and exposures (CVEs)

    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
    ingleton
    -0.08
     Gore
    -0.08
    ÅĻed
    -0.08
    ãģ°
    -0.08
    ãģ¾ãģ¾
    -0.07
    UnderTest
    -0.07
    wer
    -0.07
    elman
    -0.07
    oram
    -0.07
    orgen
    -0.07
    POSITIVE LOGITS
    ât
    0.06
     pun
    0.06
     generic
    0.06
    ua
    0.06
     Dude
    0.05
    unga
    0.05
    umann
    0.05
     CVE
    0.05
    zia
    0.05
    .gov
    0.05
    Activations Density 0.001%

    No Known Activations