© 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. 62181
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and evaluations

    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
    olation
    -0.07
    _CODEC
    -0.07
    acks
    -0.07
    efs
    -0.06
    iku
    -0.06
    _critical
    -0.06
    anon
    -0.06
     anonym
    -0.06
    ấp
    -0.06
    ahl
    -0.06
    POSITIVE LOGITS
     actually
    0.12
    actually
    0.11
     increase
    0.11
     decrease
    0.11
    increase
    0.10
     worse
    0.10
     wors
    0.09
     Actually
    0.09
    Actually
    0.09
    -net
    0.09
    Activations Density 0.186%

    No Known Activations