© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120269
    Prev
    Next
    INDEX
    Explanations

    structured lists of information, particularly related to categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Labels or descriptors that introduce structured information, typically appearing immediately before lists, tables, or enumerated items.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     mark
    -0.06
    IClient
    -0.06
    orate
    -0.06
    ]=>
    -0.06
    haus
    -0.06
    qua
    -0.05
    formation
    -0.05
    دار
    -0.05
     Aren
    -0.05
    .spy
    -0.05
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.15
    :↵
    0.15
    ):↵
    0.13
     :↵
    0.13
    :↵↵
    0.13
    ]:↵
    0.11
    ():↵
    0.11
    ï¼ļ↵
    0.11
    '):↵
    0.11
    ":↵
    0.11
    Activations Density 0.062%

    No Known Activations