© 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. 95581
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations or organizations

    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
    andi
    -0.08
    .AddListener
    -0.07
    ande
    -0.07
    bakan
    -0.06
    mlin
    -0.06
    Hang
    -0.06
    .onNext
    -0.06
    icut
    -0.06
    iya
    -0.06
    ig
    -0.06
    POSITIVE LOGITS
    okens
    0.07
     HEAP
    0.06
    .scalablytyped
    0.06
    peg
    0.06
     Awake
    0.06
    avou
    0.06
    ARAM
    0.06
    -errors
    0.06
    wing
    0.06
    gems
    0.06
    Activations Density 0.038%

    No Known Activations