© 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. 125499
    Prev
    Next
    INDEX
    Explanations

    references to remedies or remediation in various contexts

    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
    Ī
    -0.07
    erland
    -0.07
    ниÑĩ
    -0.07
    erton
    -0.06
    naments
    -0.06
    aub
    -0.06
     createSelector
    -0.06
    adle
    -0.06
    affer
    -0.06
    aan
    -0.06
    POSITIVE LOGITS
    iation
    0.09
    IGH
    0.09
    rive
    0.08
    ÄĽt
    0.07
     Mori
    0.07
    450
    0.07
    .micro
    0.07
    ive
    0.07
    ative
    0.06
    /rem
    0.06
    Activations Density 0.001%

    No Known Activations