© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56941
    Prev
    Next
    INDEX
    Explanations

    technical terms related to permissions and origins in programming 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
    loat
    -0.10
    ahun
    -0.08
    reed
    -0.07
    ocr
    -0.07
    \Blueprint
    -0.07
    elon
    -0.07
    Synopsis
    -0.06
    важ
    -0.06
    erti
    -0.06
    .sleep
    -0.06
    POSITIVE LOGITS
     cross
    0.10
     Cross
    0.09
    cross
    0.08
    -cross
    0.08
     Allow
    0.08
    _cross
    0.08
     allowed
    0.08
    .Allow
    0.07
    .cross
    0.07
    Cross
    0.07
    Activations Density 0.008%

    No Known Activations