© 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. 15-LLAMASCOPE-RES-131K
    11. 617
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of systems and vulnerabilities

    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
    362
    -0.07
    hausen
    -0.06
    _seed
    -0.06
     Seeds
    -0.06
    ein
    -0.06
    ucid
    -0.06
    Ỽ
    -0.06
    906
    -0.06
    å¹ķ
    -0.06
    iscopal
    -0.06
    POSITIVE LOGITS
    缼
    0.07
    alink
    0.07
    warts
    0.07
    ector
    0.07
    MMdd
    0.06
    ECTOR
    0.06
    aign
    0.06
    _Base
    0.06
     pcap
    0.06
    odox
    0.06
    Activations Density 0.000%

    No Known Activations