© 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. 128659
    Prev
    Next
    INDEX
    Explanations

    keywords related to states and processes in programming

    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
    seau
    -0.09
    uhan
    -0.07
     skal
    -0.07
    _SUPPORT
    -0.06
    isos
    -0.06
    ieder
    -0.06
    ILD
    -0.06
    شاء
    -0.06
     flashback
    -0.06
    æ®
    -0.06
    POSITIVE LOGITS
     status
    0.17
     state
    0.15
     statuses
    0.14
    status
    0.14
    çĬ¶æĢģ
    0.14
     Status
    0.13
    -status
    0.13
     states
    0.13
    .status
    0.12
     trạng
    0.12
    Activations Density 0.063%

    No Known Activations