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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 61923
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and transitional phrases that indicate shifts in argument or perspective

    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
    yen
    -0.06
    WISE
    -0.06
    vere
    -0.06
    bow
    -0.06
    hap
    -0.06
    Reviewer
    -0.06
    hc
    -0.06
    æľīçļĦ
    -0.06
     Eis
    -0.06
     mono
    -0.05
    POSITIVE LOGITS
    ieder
    0.10
     even
    0.09
    erken
    0.07
    çĶļèĩ³
    0.07
     tháºŃm
    0.07
    >tag
    0.07
    (Initialized
    0.07
     HÃłnh
    0.07
    èĻ½çĦ¶
    0.07
     maybe
    0.06
    Activations Density 0.030%

    No Known Activations