© 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. 125847
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or political figures

    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
    anker
    -0.08
    VICES
    -0.08
     zase
    -0.07
    bben
    -0.07
    canf
    -0.07
    lix
    -0.07
    ANJI
    -0.07
    Äįin
    -0.07
    Pink
    -0.07
    ystack
    -0.07
    POSITIVE LOGITS
     gar
    0.07
    umont
    0.07
    ãĤ±ãĥĥãĥĪ
    0.06
     Garrett
    0.06
    iot
    0.06
    sov
    0.06
    Artifact
    0.06
    imoto
    0.06
    otto
    0.06
     bet
    0.05
    Activations Density 0.000%

    No Known Activations