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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77263
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate the formation or establishment of situations and conditions

    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
    icator
    -0.07
    Reserved
    -0.07
    ickle
    -0.07
    бÑĥдÑĮ
    -0.07
    ivery
    -0.07
     vẻ
    -0.06
    tober
    -0.06
    _SU
    -0.06
     Sadd
    -0.06
     RESERVED
    -0.06
    POSITIVE LOGITS
     opportunities
    0.10
     opportunity
    0.10
     Opportunities
    0.07
    alties
    0.07
    fone
    0.07
     conditions
    0.07
     oportun
    0.07
     demand
    0.07
     an
    0.07
     problems
    0.07
    Activations Density 0.024%

    No Known Activations