© 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. 16575
    Prev
    Next
    INDEX
    Explanations

    instances of negation or phrases indicating difficulty and complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    angl
    -0.08
    dle
    -0.08
    fono
    -0.08
     киÑĪ
    -0.08
    ngrx
    -0.07
    gba
    -0.07
    isia
    -0.07
    argo
    -0.07
    iox
    -0.07
    regnum
    -0.07
    POSITIVE LOGITS
     helps
    0.10
     help
    0.10
    help
    0.09
     helped
    0.09
     ayuda
    0.08
    Help
    0.08
     Helps
    0.08
     Help
    0.08
     helping
    0.07
     giúp
    0.07
    Activations Density 0.053%

    No Known Activations