Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29447
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal opinions and subjective evaluation

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

    Words or phrases that serve as conceptual transitions or create meaningful connections between ideas in text.

    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
     permanent
    -0.07
     perman
    -0.06
     Permanent
    -0.06
     permanently
    -0.06
    ole
    -0.06
    utzer
    -0.06
     nameLabel
    -0.06
     demi
    -0.06
    agr
    -0.06
    attles
    -0.06
    POSITIVE LOGITS
     blank
    0.17
    blank
    0.16
    Blank
    0.13
     Blank
    0.13
     blanks
    0.12
     neutrality
    0.11
    .blank
    0.11
    _blank
    0.11
     empty
    0.11
    -empty
    0.11
    Activations Density 0.063%

    No Known Activations