© 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. 9-LLAMASCOPE-RES-131K
    11. 95586
    Prev
    Next
    INDEX
    Explanations

    themes of judgment, support, and rights related to healthcare and friendship

    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
    istrat
    -0.07
    mans
    -0.06
    øre
    -0.06
    neau
    -0.06
    PLIT
    -0.06
    лÑİд
    -0.06
    ito
    -0.06
     López
    -0.06
    êµIJ
    -0.06
    ered
    -0.06
    POSITIVE LOGITS
    hangi
    0.07
    adaki
    0.07
     Oper
    0.07
     rapid
    0.06
    ibel
    0.06
    omaly
    0.06
    å¾Ģ
    0.06
     Blank
    0.06
    Blank
    0.06
    .hw
    0.06
    Activations Density 0.073%

    No Known Activations