© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56993
    Prev
    Next
    INDEX
    Explanations

    negations and assertions in various forms

    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
    currently
    -0.12
     currently
    -0.11
     presently
    -0.09
     Currently
    -0.08
    Currently
    -0.08
     now
    -0.08
    缮åīį
    -0.08
    léd
    -0.08
     äºĨ
    -0.08
    combe
    -0.08
    POSITIVE LOGITS
     originally
    0.12
     yesterday
    0.10
    /is
    0.10
    nt
    0.10
     initially
    0.09
     previously
    0.09
     formerly
    0.09
    ÅĽmy
    0.09
     earlier
    0.09
     бÑĭ
    0.08
    Activations Density 0.073%

    No Known Activations