© 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. 103931
    Prev
    Next
    INDEX
    Explanations

    relational phrases and terms related to access and functionality

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

    Common connecting words and phrases that bridge different parts of text content, including prepositions, pronouns, and code identifiers appearing in various document contexts.

    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
    irit
    -0.08
    ynos
    -0.07
    gie
    -0.07
    vik
    -0.06
    ligt
    -0.06
    ampoline
    -0.06
    ellido
    -0.06
    ouble
    -0.06
    ymes
    -0.06
    vine
    -0.06
    POSITIVE LOGITS
    uria
    0.07
     takson
    0.07
    ophys
    0.06
    ếp
    0.06
    mae
    0.06
    .palette
    0.06
    æīķ
    0.06
    boss
    0.06
    encies
    0.06
     mue
    0.06
    Activations Density 0.009%

    No Known Activations