© 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. 56292
    Prev
    Next
    INDEX
    Explanations

    key technical terms and identifiers related to computing and data processing

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

    Technical terms, brand names, or identifiers that serve as specific reference points within technical documentation, code, or specialized content.

    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
    ãģ¼
    -0.08
    %c
    -0.07
    noc
    -0.07
    obao
    -0.07
    ̧
    -0.07
    azes
    -0.07
    fw
    -0.07
    ospace
    -0.07
    Äĩ
    -0.07
    ifa
    -0.07
    POSITIVE LOGITS
    incerely
    0.06
     version
    0.06
     기ì¤Ģ
    0.06
    094
    0.06
     ëķĮ문
    0.06
    484
    0.06
     Version
    0.06
    çµĮ
    0.06
    º
    0.06
     perspective
    0.06
    Activations Density 0.086%

    No Known Activations