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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119388
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and the treatment of marginalized groups

    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
    ắc
    -0.08
    大åħ¨
    -0.08
    thal
    -0.08
    ÑĢиÑĦ
    -0.08
    rax
    -0.07
    achten
    -0.07
    лоб
    -0.07
    ();++
    -0.07
    .Apis
    -0.07
    robat
    -0.07
    POSITIVE LOGITS
     Naomi
    0.07
     Jordan
    0.07
     conservative
    0.06
     cushion
    0.06
     thresh
    0.06
     patri
    0.06
     Patri
    0.06
     Ruth
    0.05
     Davidson
    0.05
     gossip
    0.05
    Activations Density 0.005%

    No Known Activations