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

    Neuronpedia

    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. 86859
    Prev
    Next
    INDEX
    Explanations

    references to selflessness and contribution to others

    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
    errick
    -0.06
     Ash
    -0.06
    omp
    -0.06
     Davidson
    -0.06
     incl
    -0.06
    aram
    -0.06
     steps
    -0.06
     scoop
    -0.06
     Uz
    -0.06
    ac
    -0.06
    POSITIVE LOGITS
    wit
    0.07
     effort
    0.07
     iconName
    0.07
    íĹĮ
    0.07
    anging
    0.07
    _DIRS
    0.07
    flo
    0.06
    vw
    0.06
    npc
    0.06
    acomment
    0.06
    Activations Density 0.013%

    No Known Activations