© 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. 15-LLAMASCOPE-RES-131K
    11. 87406
    Prev
    Next
    INDEX
    Explanations

    references to animals and animal-based research, particularly in the context of ethics and methodology

    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
    622
    -0.06
     vit
    -0.06
     vain
    -0.05
     ens
    -0.05
    624
    -0.05
     early
    -0.05
     elect
    -0.05
    ,
    -0.05
    a
    -0.05
     important
    -0.05
    POSITIVE LOGITS
    jure
    0.09
    vsp
    0.09
    !=(
    0.09
    celik
    0.08
    .createFrom
    0.08
    asics
    0.08
    ÙĬÙĤ
    0.08
    istar
    0.08
    ÑĥÑħ
    0.08
    !↵↵↵↵
    0.08
    Activations Density 0.067%

    No Known Activations