© 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. 93478
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

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

    Text fragments that appear in structured content like URLs, dates, code, or formatted lists - often single characters, spaces, or punctuation that serve as delimiters or connecting elements.

    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
    ,...↵
    -0.06
    onga
    -0.06
    interopRequireDefault
    -0.06
     RTVF
    -0.06
     بÙĪابة
    -0.06
     SHARE
    -0.06
    lam
    -0.05
     uranus
    -0.05
    odox
    -0.05
    é¾Ħ
    -0.05
    POSITIVE LOGITS
    ãĢ
    0.09
    渡
    0.08
    лоп
    0.07
    дап
    0.07
    ÑĩаÑģÑĤ
    0.07
    INLINE
    0.07
    .until
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    .Dot
    0.07
    krom
    0.07
    Activations Density 0.001%

    No Known Activations