© 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. 119383
    Prev
    Next
    INDEX
    Explanations

    instances of legal amendments and modifications

    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
    Convention
    -0.07
     tane
    -0.07
     adj
    -0.07
    hurst
    -0.07
    _Record
    -0.06
    inspection
    -0.06
     stanice
    -0.06
    adj
    -0.06
     OPTIONAL
    -0.06
    ToOne
    -0.06
    POSITIVE LOGITS
    latest
    0.07
     última
    0.07
    _latest
    0.06
     latest
    0.06
     Maid
    0.06
    ±Ð¾ÑĤ
    0.06
    itag
    0.06
    @dynamic
    0.06
    آخر
    0.06
    LOT
    0.06
    Activations Density 0.008%

    No Known Activations