© 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 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. 84232
    Prev
    Next
    INDEX
    Explanations

    concepts related to community engagement and social responsibility

    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
    .radioButton
    -0.08
    ignet
    -0.08
    rax
    -0.08
    istrovstvÃŃ
    -0.08
    .ManyToMany
    -0.08
    cimal
    -0.08
    éĺħ读次æķ°
    -0.07
    üz
    -0.07
    rita
    -0.07
    rak
    -0.07
    POSITIVE LOGITS
    -style
    0.09
    -type
    0.08
     principles
    0.08
     exercised
    0.07
     style
    0.06
     concepts
    0.06
     exercise
    0.06
     for
    0.06
     type
    0.06
     skills
    0.06
    Activations Density 0.058%

    No Known Activations