© 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. 78271
    Prev
    Next
    INDEX
    Explanations

    words related to design and creation

    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
    zens
    -0.07
    agher
    -0.07
    reur
    -0.07
    ambre
    -0.07
    469
    -0.07
    HEME
    -0.07
    ducted
    -0.07
    OrNil
    -0.06
    iform
    -0.06
    AsyncResult
    -0.06
    POSITIVE LOGITS
    ufe
    0.08
    ster
    0.06
    oby
    0.06
    rán
    0.06
    N
    0.06
    edo
    0.06
     Dor
    0.06
    abus
    0.06
    by
    0.06
     Din
    0.05
    Activations Density 0.002%

    No Known Activations