© 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. 27242
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant events or changes in circumstances

    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
    Ł
    -0.07
    .escape
    -0.06
    çµ
    -0.06
     Kro
    -0.06
    /select
    -0.06
     StringUtils
    -0.06
     merc
    -0.05
    selector
    -0.05
    HN
    -0.05
    itas
    -0.05
    POSITIVE LOGITS
     still
    0.10
     Still
    0.09
    Still
    0.09
     STILL
    0.08
    still
    0.08
     permanently
    0.08
    ä»į
    0.07
     Bios
    0.07
    è¿ĺæĺ¯
    0.07
     elsewhere
    0.07
    Activations Density 0.034%

    No Known Activations