© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    important nouns and concepts related to security and attack strategies

    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
    .scalablytyped
    -0.07
    ’S
    -0.06
    X
    -0.06
     же
    -0.06
    steder
    -0.06
    âĢª
    -0.06
    éĻ
    -0.06
    /Dk
    -0.06
    DV
    -0.06
     &
    -0.06
    POSITIVE LOGITS
    олÑİ
    0.07
     ãģ¾
    0.07
    ÙĪØ«
    0.07
    untime
    0.06
    inz
    0.06
    Experiment
    0.06
     Cascade
    0.06
    RAINT
    0.06
    andr
    0.06
    okane
    0.06
    Activations Density 0.000%

    No Known Activations